A train fire and smoke warning and prediction system and method

Abstract

The present invention discloses a train fire vehicle-cloud early warning and prediction system and method. The method includes: constructing a multi-modal fire early warning model and a multi-modal fire situation prediction model based on deep learning and training them; the on-vehicle terminal acquires multi-source heterogeneous real-time data through sensors, extracts and fuses the features of the multi-source heterogeneous real-time data, and then inputs the fused features into the trained multi-modal fire early warning model, and the highest probability state output is the real-time fire early warning result; transmitting the acquired multi-source heterogeneous real-time data to the cloud, and the cloud receives and stores the real-time data; combining the stored historical data with the real-time data, and using the trained multi-modal fire situation prediction model to extract features and conduct integrated research and judgment on all multi-source heterogeneous data to obtain the prediction of the development of the fire situation; the present invention realizes independent and accurate fire early warning under the condition of limited computing power of the on-vehicle terminal, and accurate prediction of the development of the fire situation under the condition of high computing power of the cloud.

Description

Technical Field

[0001] The present invention relates to the field of train fire early warning and prediction, and specifically discloses a train fire vehicle-cloud early warning and prediction system and method. Background Art

[0002] The background of train fires is complex, and its ignition sources include various factors such as electrical failures, illegal use of open flames, and spontaneous combustion of flammable materials. Due to the relatively enclosed space of trains, the combustibles present result in a large fire load. The interaction of factors such as air convection inside the train and surface conduction of combustibles causes the fire to spread rapidly. Generally speaking, train fires have many characteristics such as strong initial concealment, fast development speed, rapid spread of smoke, great difficulty in rescue, and large harmful impacts.

[0003] Currently, in engineering, a traditional train fire automatic alarm system is generally adopted. For physical quantities such as smoke and heat in the initial stage of a fire, they are collected through fire detectors such as smoke-temperature composite detectors and temperature-sensing cables arranged in positions such as carriages, and transmitted to the train fire alarm controller. When a single judgment data source such as the collected smoke concentration or temperature exceeds a certain threshold, an alarm signal will be generated and informed to the driver in the form of sound and light or a human-machine interface. However, due to the complex train environment, the detectors are easily interfered by the outside world and cause missed alarms and false alarms, and the reliability of the system cannot meet the requirements of real-time and accurate fire detection, and it is even more impossible to provide early fire perception and early warning and the ability to predict the future development trend of the fire situation. In recent years, fire recognition methods based on image information have been widely used in engineering. Fire image processing algorithms based on machine learning distinguish fire pixels and non-fire pixels by extracting features such as color, shape, texture, and motion features, so as to judge whether a fire has occurred. However, this method is still a single judgment data source, and the open-source dataset of machine learning is for non-train scenarios, and the effectiveness of fire recognition in the train scenario cannot be guaranteed. Summary of the Invention

[0004] The present invention aims to provide a train fire vehicle-cloud early warning and prediction system and method, which, based on a vehicle-cloud collaborative architecture, realizes independent and accurate fire early warning and rapid linkage disposal under the condition of limited on-vehicle computing power, as well as accurate prediction of the development trend of the fire situation and comprehensive emergency disposal under the condition of high computing power in the cloud; based on a multi-source heterogeneous data fusion algorithm, comprehensively represents the information fusion judgment of multi-type sensors of disaster-causing factors, and improves the accuracy and reliability of train fire early warning and prediction; based on a vehicle-ground dual communication mechanism, ensures the reliability of information transmission and the robustness of the system in case of emergencies.

[0005] A train fire vehicle-cloud early warning and prediction method provided by the present invention includes the following steps:

[0006] Construct a multi-modal fire warning model and a multi-modal fire situation prediction model based on deep learning, and train the multi-modal fire warning model and the multi-modal fire situation prediction model to obtain the trained multi-modal fire warning model and multi-modal fire situation prediction model;

[0007] Obtain multi-source heterogeneous real-time data through sensors installed on the train, including temperature data, smoke data, wind speed data, and fire image data; extract and fuse the features of the multi-source heterogeneous real-time data, and then input the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire. The state with the highest probability output is the real-time fire warning result, and an audible and visual warning or alarm signal for the fire state is output, providing a method for independent and accurate fire warning and rapid linkage disposal under the condition of limited computing power on the vehicle-mounted side;

[0008] Transmit the multi-source heterogeneous real-time data obtained through sensors to the cloud, and the cloud receives and stores the real-time data; combine the stored historical data with the real-time data, and use the trained multi-modal fire situation prediction model to extract and fuse and analyze the features of all multi-source heterogeneous data to obtain the prediction of the development of the fire situation, providing a method for accurate prediction of the development of the fire situation and comprehensive emergency disposal under the condition of high computing power in the cloud.

[0009] Further, the multi-source heterogeneous real-time data is specifically:

[0010] The temperature data is collected by an optical fiber temperature sensor, measuring the temperature along the entire length of the train carriage, which is one-dimensional spatial data;

[0011] The smoke data is collected by a smoke sensor, and the wind speed data is collected by a wind speed sensor. The smoke sensor and the wind speed sensor respectively collect the smoke and wind speed in the train carriage, both of which are one-dimensional time data measured at spatial points;

[0012] The fire image data is collected by a visible light image sensor or / and an infrared image sensor, measuring the planar image in the train carriage, which is 2D spatial data.

[0013] Further, the method of extracting and fusing the features of the multi-source heterogeneous real-time data, and then inputting the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire, and the state with the highest probability output is the real-time fire warning result:

[0014] (1) Extract the features of the multi-source heterogeneous real-time data through a feature extraction network:

[0015] The temperature data is a one-dimensional spatial sequence. First, the temperature data is transformed into two-dimensional image-like data using the method of discrete wavelet transform, and then a convolutional neural network (CNN) is used to extract features from it. The CNN includes a convolutional layer, an attention module, a pooling layer, and a normalization layer;

[0016] The flue gas data and wind speed data are one-dimensional time series data of spatial points, and an LSTM model with a self-attention mechanism is used to extract features from them respectively. The LSTM model includes an LSTM layer, an attention layer, and a fully connected layer;

[0017] The fire image data is two-dimensional spatial data, and an improved VGG16 model is used to extract features from it. The VGG16 model includes a convolutional layer, an attention module, a pooling layer, and a normalization layer;

[0018] (2) Using the extracted temperature features, flue gas features, wind speed features, and fire image features as input elements, input them into the feature fusion module of the MS-FRFM network built for feature fusion to obtain the fusion features of multi-source heterogeneous real-time data;

[0019] (3) Input the fusion features into a multi-layer perceptron (MLP) network model with a double hidden layer for decision-making. The output neurons are the real-time fire state probabilities of no fire, smoldering, and open fire, and the state with the highest output probability is the real-time fire warning result.

[0020] Furthermore, the method for obtaining the prediction of the development of the fire situation by using the trained multi-modal fire situation prediction model to extract features and conduct fusion research and judgment on all multi-source heterogeneous data is as follows:

[0021] First, feature extraction is performed based on the Transformer architecture, then cross-modal cross-attention mechanism is used for modal interaction to achieve feature fusion, and then the fusion features are used as input elements. The prediction of the development of the fire situation is obtained by using a two-layer long short-term memory (LSTM) network and a multi-layer perceptron (MLP) network model.

[0022] A train fire and cloud warning prediction system, the system includes:

[0023] An on-vehicle controller, through which the on-vehicle controller realizes real-time warning of train fires based on a multi-modal fire warning model and links the train fire linkage control system;

[0024] A transmission network, which transmits on-vehicle real-time data to the cloud;

[0025] The cloud, the cloud receives and stores real-time data through a storage platform, and realizes the prediction of the development of the train fire situation based on a multi-modal fire situation prediction model through a computing platform.

[0026] Further, the vehicle-mounted controller specifically includes:

[0027] A data acquisition module that acquires multi-source heterogeneous real-time data collected by sensors installed on the train, including temperature data, smoke data, wind speed data, and fire image data;

[0028] A data fusion and processing module that extracts and fuses features from the multi-source heterogeneous real-time data, then inputs the fused features into a decision model to give the real-time fire status probabilities of no fire, smoldering fire, and flaming fire, and the state with the highest probability output is the real-time fire warning result;

[0029] A display module that displays the real-time data collected by the data acquisition module, the real-time processing process of the data fusion and processing module, the fire warning result, and the acoustic and optical warning or alarm signals of the fire status;

[0030] A linkage control interface module for connecting to the train fire linkage control system to achieve precise and rapid train fire disposal on the vehicle-mounted side.

[0031] Further, the transmission network specifically includes:

[0032] A 5G network for data transmission between the vehicle-mounted side and the cloud;

[0033] A LoRa network for data transmission between the vehicle-mounted side and the cloud in the case of vehicle-to-ground communication failure in a self-organizing network mode.

[0034] Further, the cloud specifically includes:

[0035] A storage platform for storing the real-time data output by the transmission network;

[0036] A computing platform that provides the computing power conditions for combining the stored historical data with the real-time data to achieve fire prediction, is used for predicting the development of the fire situation, reducing the probability of train fires, providing effective guarantee for train emergency disposal, and improving the safe operation level of the train.

[0037] A non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements a train fire vehicle-cloud warning and prediction method as described above.

[0038] An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements a train fire vehicle-cloud warning and prediction method as described above.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] (1)The present invention provides a train fire vehicle-cloud early warning and prediction system and method. Through the collaborative work of the on-vehicle controller, transmission network, and cloud, it realizes independent and accurate fire early warning detection and rapid linkage disposal capabilities under the condition of limited computing power on the vehicle side, as well as accurate prediction of the development of the fire situation and comprehensive emergency disposal capabilities under the condition of high computing power in the cloud, providing effective guarantee for the safe operation of the train;

[0041] (2)The present invention provides a train fire vehicle-cloud early warning and prediction system and method. Based on the multi-source heterogeneous data fusion algorithm, it comprehensively fuses and judges information from multiple types of sensors, effectively reducing the interference of noise from a single data source on the judgment result, and significantly improving the accuracy and reliability of train fire early warning and prediction;

[0042] (3)The present invention provides a train fire vehicle-cloud early warning and prediction system and method. The system performs vehicle-ground transmission through a dual communication mechanism of 5G and LoRa self-organizing network, providing double guarantee for information transmission in case of emergencies such as fire on the train, and effectively improving the robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 FIG. is a schematic diagram of the composition of a train fire vehicle-cloud early warning and prediction system proposed by the present invention. Among them, 1 is the on-vehicle controller, 2 is the transmission network, and 3 is the cloud;

[0044] Figure 2 FIG. shows the main modules of the on-vehicle controller in a train fire vehicle-cloud early warning and prediction system proposed by the present invention;

[0045] Figure 3 FIG. shows the image data in the open fire state of a set of train fire multi-source heterogeneous data selected for simulation in an embodiment of the present invention;

[0046] Figure 4 FIG. shows the evaluation result of the accuracy of the real-time fire status early warning method on the vehicle side in an embodiment of the present invention;

[0047] Figure 5 FIG. shows the evaluation result of the accuracy of the fire situation development prediction method in the cloud in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer, the following further describes the embodiments of the present invention in detail.

[0049] Embodiment 1

[0050] This embodiment provides a train fire vehicle-cloud early warning and prediction method, including the following steps:

[0051] Construct a multi-modal fire warning model and a multi-modal fire situation prediction model based on deep learning, and train the multi-modal fire warning model and the multi-modal fire situation prediction model to obtain the trained multi-modal fire warning model and multi-modal fire situation prediction model;

[0052] Obtain multi-source heterogeneous real-time data through sensors installed on the train, including temperature data, smoke data, wind speed data, and fire image data; extract and fuse the features of the multi-source heterogeneous real-time data, and then input the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire. The state with the highest probability output is the real-time fire warning result, and an audible and visual warning or alarm signal for the fire state is output, providing a method for independent and accurate fire warning and rapid linkage disposal under the condition of limited computing power on the vehicle-mounted side;

[0053] Transmit the obtained multi-source heterogeneous real-time data to the cloud, and the cloud receives and stores the real-time data; combine the stored historical data with the real-time data, and use the trained multi-modal fire situation prediction model to extract and fuse and analyze all the multi-source heterogeneous data to obtain the prediction of the development of the fire situation, providing a method for accurate prediction of the development of the fire situation and comprehensive emergency disposal under the condition of high computing power in the cloud.

[0054] The multi-source heterogeneous real-time data is specifically:

[0055] The temperature data is collected by an optical fiber temperature sensor, measuring the temperature along the entire length of the train carriage, which is one-dimensional spatial data;

[0056] The smoke data is collected by a smoke sensor, and the wind speed data is collected by a wind speed sensor. The smoke sensor and the wind speed sensor respectively collect the smoke and wind speed in the train carriage, both of which are one-dimensional time data measured at spatial points;

[0057] The fire image data is collected by a visible light image sensor or / and an infrared image sensor, measuring the planar image in the train carriage, which is 2D spatial data.

[0058] A method for extracting and fusing the features of multi-source heterogeneous real-time data, and then inputting the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire, and the state with the highest probability output is the real-time fire warning result:

[0059] (1) Extract the features of the multi-source heterogeneous real-time data through a feature extraction network;

[0060] The temperature data is a one-dimensional spatial sequence. First, the temperature data is transformed into two-dimensional image-like data using the method of discrete wavelet transform, and then a convolutional neural network (CNN) is used to extract features from it. The CNN includes a convolutional layer, an attention module, a pooling layer, and a normalization layer;

[0061] The flue gas data and wind speed data are one-dimensional time series data of spatial points, and the LSTM model with a self-attention mechanism is used to extract features from them respectively. The LSTM model includes an LSTM layer, an attention layer, and a fully connected layer;

[0062] The fire image data is two-dimensional spatial data, and an improved VGG16 model is used to extract features from it. The model includes a convolutional layer, an attention module, a pooling layer, and a normalization layer;

[0063] (2) The extracted temperature features, flue gas features, wind speed features, and fire image features are used as input elements and input into the MS-FRFM feature fusion module for feature fusion to obtain the fusion features of multi-source heterogeneous real-time data;

[0064] (3) The fusion features are input into a multi-layer perceptron (MLP) network model with a double hidden layer for decision-making. The output neurons are the real-time fire state probabilities of no fire, smoldering, and open fire, and the state with the highest output probability is the real-time fire warning result.

[0065] The method for obtaining the prediction of the development of the fire situation by using the trained multi-modal fire situation prediction model to extract features and conduct fusion research and judgment on all multi-source heterogeneous data is as follows:

[0066] First, feature extraction is performed based on the Transformer architecture, then cross-modal cross-attention mechanism is used for modal interaction to achieve feature fusion, and then the fusion features are used as input elements, and the development of the fire situation is predicted by using two layers of long short-term memory (LSTM) and a multi-layer perceptron (MLP) network model.

[0067] Specifically, in this embodiment, the specific processing process of using the trained multi-modal fire warning model to extract features and conduct fusion research and judgment on multi-source heterogeneous real-time data to obtain the real-time fire state warning of the vehicle-mounted terminal is as follows:

[0068] Step 1: Build a full-size train model, select a certain train model for 1:1 full-size simulation. In this embodiment, the selected train is 197 m long and includes 8 carriages;

[0069] Step 2: Construct a train fire simulation dataset, set the fire point location, fire heat release rate, sensor location and parameters, etc., simulate the train fire combustion process, simulate different fire conditions, and obtain 1,800 sets of multi-source heterogeneous datasets. Each set of data contains four categories: temperature, smoke, wind speed, and fire image. The dataset is annotated by manually dividing it into three categories: no fire, smoldering, and open flame. The annotated dataset is divided into training set and validation set in a 4:1 ratio.

[0070] Step 3: Preprocessing of multi-source heterogeneous data. This embodiment uses a set of multi-source heterogeneous data of train fire as an example for illustration.

[0071] Temperature data was collected at 508 points along the entire length of the carriage. The data format was 1×508, which is 1D spatial data. Table 1 shows the partial temperature data for the carriage at that moment. Tables 2 and 3 show the smoke and wind speed data for the carriage at that moment, respectively. They are 1D time data with a collection rate of 11 times per second and a data format of 1×11. It should be noted that the data in Tables 1, 2, and 3 cannot be displayed in one line, so they are processed into multiple lines using carriage returns. Figure 3 The image of a certain compartment at a certain moment is 2D spatial data in the format of 1920×1080.

[0072] Table 1

[0073]

[0074] Table 2

[0075]

[0076] Table 3

[0077]

[0078] The specific preprocessing process is to perform tensor conversion on the temperature data, perform standardization processing with a mean of 0 and a standard deviation of 1, and apply discrete wavelet transform to convert the 1×508 temperature data into a 1×10×60 image-like data format. The 1 in 1×10×60 indicates that the number of channels in the image-like data format is 1, 10 indicates that the height of the image-like data format is 10, and 60 indicates that the width of the image-like data format is 60; the smoke data and wind speed data are standardized with a mean of 0 and a standard deviation of 1, and the data format is converted to 1×11; the image data is scaled and standardized by channel, and the data format is converted to 3×244×244;

[0079] Step 4: Extract and fuse the features of multi-source heterogeneous real-time data, then input the fused features into the trained multi-modal fire warning model to obtain the real-time fire state probabilities of no fire, smoldering, and open fire, and select the state with the highest probability as the real-time fire warning result:

[0080] 1. Feature extraction: Different feature extraction networks are used for feature extraction according to the differences in data nature and structure:

[0081] (1) Extract the features of the temperature data of the one-dimensional spatial sequence after discrete wavelet transform using the VGG16 structure with 8 convolutional layers; after each convolutional layer, batch normalization is performed using BatchNorm2d, a CBAM attention module is added to enhance feature representation, and a residual module is added to avoid information loss, and the resulting feature size is 128×1×1;

[0082] (2) For the smoke and wind speed data of the one-dimensional time series, the LSTM_attention network is used for feature extraction respectively; the LSTM_attention network architecture consists of an LSTM layer, a self-attention layer, an LSTM layer, and a fully connected layer, and the resulting feature size is 128×1×1;

[0083] (3) For the fire image data with the two-dimensional spatial sequence scaled to a size of 3×244×244, an improved version of the VGG16 network is used to extract features; this network contains 10 convolutional layers, a CBAM module attention module is added, batch normalization is performed on the first 8 convolutional layers using BatchNorm2d, and the last 2 convolutional layers are used to enhance channel features, and the resulting feature size is 128×1×1;

[0084] 2. Feature fusion: The temperature, smoke, wind speed, and fire image features with a size of 128×1×1 obtained by feature extraction are used as four input elements, and the MS-FRFM network feature fusion module is used to fuse the features to obtain the fused features of multi-source information. The network effectively captures the global and local information between different feature channels through a multi-scale channel attention mechanism; further feature extraction is performed through a one-dimensional convolutional neural network 1D-CNN, and the extraction result is converted into a weight using the Sigmoid operation to highlight the key features in the original information, and the weights of the modal features are assigned based on this to achieve the full and effective fusion of the four modal features.

[0085] 3. Fire decision-making: The fused features are used as input elements and input into an MLP network model with a double hidden layer for decision-making. The output neurons are no fire, smoldering, and open fire, and the resulting output sequence is 1×3, which respectively represent the probabilities of the three real-time fire states. Select the state with the highest probability as the result of real-time fire state judgment.

[0086] In this step, the training and verification process of the multimodal fire warning model uses Cross-Entropy as the loss function for evaluation.

[0087]

[0088] in, is the probability that the true label of sample x is class i, is the probability that the model predicts that sample x is of class i, C is the total number of classes, is the cross entropy loss of the current sample x.

[0089] This example trains for 200 epochs, and the learning rate for the first 100 epochs is 2.5×10 -5 , the learning rate for the next 100 epochs is 2.5×10 -6 After training for 200 epochs, the loss reaches 1.1×10 -3 The fire status detection accuracy can reach 98.8%. Figure 4 As shown in the figure, the horizontal axis is the number of training rounds and the vertical axis is the accuracy.

[0090] In this embodiment, the trained multimodal fire situation prediction model is used to extract features and perform fusion analysis on all multi-source heterogeneous data to obtain the specific process of cloud-based fire situation development prediction:

[0091] Step 1: The collected multi-source heterogeneous real-time data, namely train temperature, smoke, wind speed, and fire image data, is transmitted to a cloud storage platform using a 5G or LoRa transmission network;

[0092] In the second step, the computing platform combines the stored historical data with the real-time data to calculate the fire situation development forecast. The processing process is consistent with the on-board detection method path, and features are extracted and fused for multi-source heterogeneous data. The network model selected under high computing power conditions is as follows: first, feature extraction is performed based on the Transformer architecture, and then a cross-modal cross-attention mechanism is used for modal interaction to achieve feature fusion. The fused features are then used as input elements, and a two-layer LSTM and MLP network model is used to obtain the fire situation development forecast. Figure 5 Taking the fire situation as an example to demonstrate the effectiveness of this network model, its situation development prediction trend (the predicted value marked in the figure) is consistent with the trend of the simulated fire development simulation result (the true value marked in the figure), where the horizontal axis is time and the vertical axis is heat release rate.

[0093] Example 2

[0094] This embodiment describes a train fire vehicle-cloud early warning and prediction system, including a vehicle-mounted controller 1, a transmission network 2, and a cloud 3.Figure 1 as shown

[0095] The vehicle-mounted controller specifically includes, as Figure 2 shown: The data acquisition module obtains multi-source heterogeneous real-time data from various types of sensors installed on the train, including temperature, smoke, wind speed, and fire images; the data fusion processing module extracts and fuses the features of the multi-source heterogeneous real-time data, then inputs the fused features into the decision model to give the real-time fire state probabilities of no fire, smoldering, and open fire, and outputs the highest probability state as the real-time fire warning result; the display module displays the real-time data collected by the data acquisition module, the real-time processing process of the data fusion processing module, the fire warning result, and the acoustic and optical warning or alarm signals of the fire state; the linkage control interface module is used to connect to the train fire linkage control system to achieve accurate and rapid train fire disposal on the vehicle-mounted side;

[0096] The transmission network specifically includes 5G and LoRa, where 5G is used for data transmission between the vehicle-mounted side and the cloud when vehicle-ground communication is normal, and LoRa is used for data transmission between the vehicle-mounted side and the cloud in a self-organizing network mode when vehicle-ground communication fails;

[0097] The cloud specifically includes a storage platform and a computing platform, where the storage platform is used to store the real-time data output by the transmission network; the computing platform provides the computing power conditions for combining the stored historical data with the real-time data to achieve fire prediction, is used for predicting the development of the fire situation, reduces the probability of train fires, provides effective guarantee for train emergency disposal, and improves the safe operation level of the train.

[0098] This embodiment also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements a train fire vehicle-cloud warning and prediction method as described above.

[0099] Furthermore, the present invention adopts the following technical solutions:

[0100] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a train fire vehicle-cloud warning and prediction method as described above.

[0101] Through the description of the above embodiments, those skilled in the art can clearly understand that the facilities of the present invention can be implemented by means of software plus a necessary general hardware platform. The embodiments of the present invention can be implemented using existing processors, or by dedicated processors used for this purpose or other purposes in a suitable system, or by a hardwired system. The embodiments of the present invention also include non-transitory computer-readable storage media, which include machine-readable media for carrying or having machine-executable instructions or data structures stored thereon; such machine-readable media can be any available media accessible by a general or special-purpose computer or other machine with a processor. For example, such machine-readable media can include RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk memories, magnetic disk memories or other magnetic storage devices, or any other medium that can be used to carry or store the required program code in the form of machine-executable instructions or data structures and can be accessed by a general or special-purpose computer or other machine with a processor. When information is transmitted or provided to a machine through a network or other communication connection (hardwired, wireless, or a combination of hardwired and wireless), this connection is also regarded as a machine-readable medium.

[0102] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for predicting train fire and smoke warning, characterized in that, It includes the following steps: Construct a multi-modal fire warning model and a multi-modal fire situation prediction model based on deep learning, and train the multi-modal fire warning model and the multi-modal fire situation prediction model to obtain the trained multi-modal fire warning model and multi-modal fire situation prediction model; Obtain multi-source heterogeneous real-time data through sensors installed on the train, including temperature data, smoke data, wind speed data, and fire image data; extract and fuse the features of the multi-source heterogeneous real-time data, and then input the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire. The state with the highest probability output is the real-time fire warning result, and an audible and visual warning or alarm signal of the fire state is output; Transmit the multi-source heterogeneous real-time data obtained through the sensors to the cloud, and the cloud receives and stores the real-time data; combine the stored historical data with the real-time data, and use the trained multi-modal fire situation prediction model to extract features and conduct integrated research and judgment on all multi-source heterogeneous data to obtain the prediction of the development of the fire situation; The multi-source heterogeneous real-time data is specifically: The temperature data is collected by an optical fiber temperature sensor, and the temperature along the entire length of the train car is measured, which is one-dimensional spatial data; The smoke data is collected by a smoke sensor, and the wind speed data is collected by a wind speed sensor. The smoke sensor and the wind speed sensor respectively collect the smoke and wind speed in the train car, both of which are one-dimensional time data measured at spatial points; The fire image data is collected by a visible light image sensor or / and an infrared image sensor, and the planar image in the train car is measured, which is 2D spatial data; The method of extracting and fusing the features of the multi-source heterogeneous real-time data, and then inputting the fused features into the trained multi-modal fire warning model to give the real-time fire state probabilities of no fire, smoldering, and open fire, and the state with the highest probability output is the real-time fire warning result: (1) Extract the features of the multi-source heterogeneous real-time data through a feature extraction network: The temperature data is a one-dimensional spatial sequence. First, use the method of discrete wavelet transform to transform the temperature data into two-dimensional image-like data, and then use a convolutional neural network CNN to extract features from it. The convolutional neural network CNN includes a convolutional layer, an attention module, a pooling layer, and a normalization layer; The smoke data and the wind speed data are one-dimensional time series data at spatial points, and a long short-term memory (LSTM) model with a self-attention mechanism is used to extract features from them respectively. The LSTM model includes an LSTM layer, an attention layer, and a fully connected layer; The fire image data is two-dimensional spatial data, and an improved VGG16 model is used to extract features from it. The VGG16 model includes a convolutional layer, an attention module, a pooling layer, and a normalization layer; (2) Take the extracted temperature features, smoke features, wind speed features, and fire image features as input elements, and input them into the feature fusion module of the MS-FRFM network built to perform feature fusion to obtain the fused features of the multi-source heterogeneous real-time data; (3) Input the fused features into a multi-layer perceptron (MLP) network model with a double hidden layer for decision-making. The output neurons are the probabilities of the real-time fire states of no fire, smoldering, and flaming, and the state with the highest output probability is the real-time fire warning result.

2. The train fire cloud warning and prediction method according to claim 1, wherein The method for obtaining the prediction of the development of the fire situation by using the trained multi-modal fire situation prediction model to extract features and conduct fusion research and judgment on all multi-source heterogeneous data is as follows: First, perform feature extraction based on the Transformer architecture, then use the cross-modal cross-attention mechanism for modal interaction to achieve feature fusion, and then use the fused features as input elements. Use a two-layer long short-term memory (LSTM) network and a multi-layer perceptron (MLP) network model to obtain the prediction of the development of the fire situation.

3. A system for a train fire and plume warning and prediction method according to claim 1 or 2, characterized in that, The system includes: A vehicle-mounted controller, which realizes real-time fire warning of the train based on the multi-modal fire warning model and links the train fire linkage control system through the vehicle-mounted controller; A transmission network, which transmits the real-time data at the vehicle-mounted end to the cloud; The cloud, which receives and stores the real-time data through the storage platform and realizes the prediction of the development of the train fire situation based on the multi-modal fire situation prediction model through the computing platform.

4. The train fire and cloud warning and prediction system according to claim 3, wherein The vehicle-mounted controller specifically includes: A data acquisition module, which acquires multi-source heterogeneous real-time data through sensors installed on the train, including temperature data, smoke data, wind speed data, and fire image data; A data fusion processing module, which extracts and fuses the features of the multi-source heterogeneous real-time data, then inputs the fused features into the decision model, gives the probabilities of the real-time fire states of no fire, smoldering, and flaming, and the state with the highest output probability is the real-time fire warning result; A display module, which displays the real-time data acquired by the data acquisition module, the real-time processing process of the data fusion processing module, the fire warning result, and the sound and light warning or alarm signal of the fire state; A linkage control interface module, which is used to connect the train fire linkage control system to achieve precise and rapid train fire disposal at the vehicle-mounted end.

5. The train fire cloud warning and prediction system according to claim 3, characterized in that, The transmission network specifically includes: A 5G network, which is used for data transmission between the vehicle-mounted end and the cloud; A LoRa network, which is used for data transmission between the vehicle-mounted end and the cloud in the case of the failure of vehicle-to-ground communication in a self-organizing network mode.

6. The train fire and cloud warning and prediction system according to claim 3, characterized in that, The cloud specifically includes: A storage platform, which is used to store the real-time data output by the transmission network; A computing platform, which provides the computing power conditions for combining the stored historical data and real-time data to achieve fire pre-judgment and is used for predicting the development of the fire situation.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements a method for train fire vehicle-cloud warning and prediction as described in any one of claims 1 to 2.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements a method for train fire vehicle-cloud warning and prediction as described in any one of claims 1 to 2.

Images