A fire determination method, device, equipment, medium and product

Abstract

This invention discloses a fire determination method, apparatus, equipment, medium, and product. The method includes: responding to a fire determination request within a target compartment, determining sensor data collected by preset temperature sensors, gas sensors, and visual sensors; analyzing and processing the temperature data, gas concentration data, and visual image data from the sensor data to obtain temperature characteristics, gas characteristics, and visual characteristics; based on a preset fusion strategy, determining the fire confidence level of a fire occurring within the target compartment according to the temperature characteristics, gas characteristics, and visual characteristics, thereby determining the fire determination result and responding to the fire determination request. The technical solution of this invention can perform a more comprehensive analysis of fire conditions from three levels: temperature, gas concentration, and visual recognition. Combined with a preset fusion strategy, it can quickly assess the fire confidence level, effectively improving the timeliness and accuracy of fire identification.

Description

Technical Field

[0001] This invention relates to the field of big data, and in particular to a method, apparatus, equipment, medium and product for fire detection. Background Technology

[0002] Traditional fire detection methods in the vehicle compartments of roll-on / roll-off (Ro-Ro) ships rely heavily on single sensors (such as smoke and heat detectors). Detectors are installed on the roof of the vehicle compartment. Each heat detector has a maximum coverage area of ​​37 m², with a maximum distance of 9 m between their center points; each smoke detector has a maximum coverage area of ​​74 m², with a maximum distance of 11 m between their center points. These detectors are effective for smoke-induced fires with significant temperature rise and exposure. However, they suffer from high false alarm rates, response delays, and missed detections. This is particularly problematic for Ro-Ro ship vehicle compartments, which have complex internal spaces, dense cargo, and high fire hazards. Furthermore, with the increasing number of lithium-ion battery-powered new energy vehicles being transported in recent years, traditional smoke and heat detectors cannot respond quickly or accurately detect fires caused by the heating of the battery compartments in these vehicles. Therefore, using traditional fire detection technologies and methods to address the transport of new energy vehicles on ships is insufficient from a safety perspective and unreliable from a performance perspective.

[0003] Therefore, how to reasonably, effectively, and accurately optimize the fire detection system inside ship vehicle compartments to improve the timeliness and accuracy of fire detection is an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a fire detection method, apparatus, equipment, medium, and product to conduct a more comprehensive analysis of fire conditions from three levels: temperature, gas concentration, and visual recognition. It combines a preset fusion strategy to quickly assess the fire confidence level, effectively improving the timeliness and accuracy of fire detection.

[0005] According to one aspect of the present invention, a fire determination method is provided, comprising: In response to a request to determine a fire in the target compartment, the sensor data collected by the preset temperature sensor, gas sensor and vision sensor are determined. Temperature data, gas concentration data, and visual image data from the sensor data are analyzed and processed to obtain temperature characteristics, gas characteristics, and visual characteristics. Based on a pre-defined fusion strategy, the fire confidence level of a fire occurring in the target compartment is determined according to temperature characteristics, gas characteristics, and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

[0006] According to another aspect of the present invention, a fire detection device is provided, comprising: The determination module is used to determine the sensor data collected by the preset temperature sensor, gas sensor and vision sensor in response to the fire determination request in the target compartment. The analysis module is used to analyze and process the temperature data, gas concentration data and visual image data in the sensor data respectively to obtain temperature features, gas features and visual features. The response module is used to determine the fire confidence level of a fire occurring in the target compartment based on a preset fusion strategy, according to temperature characteristics, gas characteristics, and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fire determination method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the fire determination method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is also provided, which includes a computer program that, when executed by a processor, implements the fire determination method of any embodiment of the present invention.

[0010] The technical solution of this invention, in response to a fire determination request within a target compartment, determines sensor data collected by preset temperature sensors, gas sensors, and visual sensors; analyzes and processes the temperature data, gas concentration data, and visual image data from the sensor data to obtain temperature features, gas features, and visual features; based on a preset fusion strategy, determines the fire confidence level of a fire occurring within the target compartment according to the temperature features, gas features, and visual features, thereby determining the fire determination result and responding to the fire determination request. By conducting a more comprehensive analysis of the fire situation from three levels—temperature, gas concentration, and visual recognition—and combining this with a preset fusion strategy to quickly assess the fire confidence level, the timeliness and accuracy of fire identification can be effectively improved.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a fire determination method provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of a fire detection device provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," "target," "candidate," and "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the invention described herein can be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The acquisition, storage, use, and processing of data in the technical solutions of this application comply with relevant laws and regulations.

[0016] Example 1 Figure 1This is a flowchart of a fire determination method provided by an embodiment of the present invention. This embodiment is applicable to situations where a more comprehensive analysis of a fire situation is performed from three levels: temperature, gas concentration, and visual recognition. Combined with a preset fusion strategy, the fire confidence level is quickly assessed. This method can be executed by a fire determination device, which can be implemented in hardware and / or software. The fire determination device can be configured in an electronic device, such as... Figure 1 As shown, the fire determination method includes: S101. In response to a request to determine a fire in the target compartment, determine the sensor data collected by the preset temperature sensor, gas sensor, and vision sensor.

[0017] The target compartment refers to the vehicle compartment within the ship; a fire determination request is a request to analyze the confidence level of a fire occurring within the target compartment and to issue a timely fire warning. Temperature sensors can be distributed fiber optic temperature detectors and infrared thermal imagers.

[0018] The number of temperature sensors can be at least two, and the temperature sensors can be evenly distributed along the top of the vehicle compartment to monitor the temperature field inside the compartment in real time. Specifically, they are configured at at least two temperature measuring points on the top of the vehicle compartment. The gas sensors can be at least two preset gas detectors, and the gas sensors are configured at the bottom of the vehicle compartment to collect the gas concentration of the preset target gas.

[0019] The visual sensor can be a high-resolution visible light dual-mode camera, configured on the top of the vehicle compartment. The visual sensor can support the recognition of flames and smoke in low light conditions (such as below 0.01 Lux). The sensing data includes temperature data, gas concentration data, and visual image data. Temperature data is acquired through distributed fiber optic temperature detectors and infrared thermal imagers, gas concentration data is acquired through gas detectors, and visual image data is acquired through visible light dual-mode cameras.

[0020] Optionally, the sensor data collected by the preset temperature sensor, gas sensor, and vision sensor are determined, including: using a preset distributed fiber optic temperature detector to collect the local temperature inside the target cabin, and using an infrared thermal imager to collect the spatial temperature distribution map inside the target cabin, to determine the temperature data collected by the preset temperature sensor; using a preset gas detector to detect the gas concentration of the target gas inside the target cabin, to determine the gas concentration data collected by the gas sensor; and using a preset visible light dual-mode camera to collect video data of a preset duration inside the target cabin, to determine the visual image data collected by the vision sensor.

[0021] The target gas includes at least one of the following: carbon monoxide (CO), hydrogen (H2), and volatile organic compounds (VOCs).

[0022] S102. Analyze and process the temperature data, gas concentration data and visual image data in the sensor data respectively to obtain temperature characteristics, gas characteristics and visual characteristics.

[0023] Temperature characteristics may include the local temperature rise rate and the area ratio of high-temperature regions. Gas characteristics may include the calibrated carbon monoxide concentration, hydrogen concentration, and hydrocarbon gas concentration, and may also include the hydrocarbon gas concentration and the calibrated carbon monoxide to hydrocarbon gas concentration ratio. Visual characteristics may include information such as the flame color, edge fractal dimension, and flicker frequency identified inside the target cabin.

[0024] Optionally, the temperature data in the sensing data is analyzed and processed to obtain temperature characteristics, including: determining the temperature data in the sensing data; analyzing the local temperature collected by the distributed fiber optic temperature detector within a preset analysis period to determine the local temperature rise rate; determining the area ratio of high-temperature regions in the temperature distribution map based on the temperature distribution map collected by the infrared thermal imager and the preset high-temperature threshold, and determining the temperature characteristics based on the local temperature rise rate and the area ratio of high-temperature regions.

[0025] The temperature data includes local temperatures collected by distributed fiber optic temperature detectors and temperature distribution maps collected by infrared thermal imagers.

[0026] Optionally, the local temperatures collected by the distributed fiber optic temperature detectors within the preset analysis period can be filtered to determine the termination temperature and the initial temperature, and the temperature difference between the termination temperature and the initial temperature can be determined. The ratio of the temperature difference to the corresponding duration of the preset analysis period can be determined as the local temperature rise rate.

[0027] Optionally, the number of high-temperature pixels exceeding a preset high-temperature threshold in the temperature distribution map acquired by the infrared thermal imager can be determined, and the ratio of the number of high-temperature pixels to the total number of pixels in the temperature distribution map can be determined as the area ratio of the high-temperature region in the temperature distribution map.

[0028] Optionally, the gas concentration data in the sensing data is analyzed and processed to obtain gas features, including: determining the gas concentration data of the target gas in the sensing data; performing baseline calibration on the gas concentration data based on a preset dynamic threshold method to eliminate background noise and obtain calibrated gas concentration data; determining an initial feature vector based on the calibrated gas concentration data, and performing normalization and principal component analysis on the initial feature vector to obtain a principal component score matrix as the gas features.

[0029] The initial feature vector includes the calibrated carbon monoxide concentration, calibrated hydrogen concentration, calibrated hydrocarbon gas concentration, and the ratio of the calibrated hydrocarbon gas concentration to the calibrated carbon monoxide concentration. The calibrated carbon monoxide concentration can reflect the net CO signal after removing environmental drift, the calibrated hydrogen concentration can capture H2 release characteristics related to pyrolysis or chemical reactions, the calibrated hydrocarbon gas concentration can indicate the intensity of organic combustion or leakage, and the ratio of the hydrocarbon gas concentration to the calibrated carbon monoxide concentration can characterize combustion efficiency or pollution source type.

[0030] Principal Component Analysis (PCA) is used to reduce the dimensionality and decorrelate the initial feature vector, extract the orthogonal features that explain the largest variance, thereby highlighting the main variation patterns in the CO / VOCs ratio and removing noise redundancy.

[0031] Optionally, the initial feature vector can be Z-score normalized to eliminate dimensional differences and ensure fair weight allocation in PCA. Furthermore, through steps such as calculating the covariance matrix, eigenvalue decomposition, and selecting principal components, principal component analysis is performed on the normalized initial feature vector to obtain the principal component score matrix, which is the extracted low-dimensional feature and serves as the gas feature.

[0032] Optionally, the visual image data in the sensing data is analyzed and processed to obtain visual features, including: using a preset target detection model to perform target detection on the visual image data in the sensing data to obtain the target analysis image corresponding to the flame region; and extracting features from the target analysis image based on a pre-trained convolutional neural network to determine the flame color, edge fractal dimension, and flicker frequency corresponding to the target analysis image to obtain visual features.

[0033] The target detection model can be the YOLO model (You Only Look Once), used to locate the flame region in the visual image data and obtain the target analysis image. The target analysis image refers to the region image corresponding to the flame region in the visual image data.

[0034] Optionally, the target analysis image can be converted to the HSV color space (Hue, Saturation, Value) to enhance the sensitivity to the orange and red main colors of the flame. The first layer of the convolutional neural network can be used to automatically learn the color distribution pattern of the flame, capturing the high saturation and medium-high brightness areas to determine the flame color. Based on the pre-trained convolutional neural network, the irregularity and dynamic diffusion pattern of the flame edge can be detected by using shallow convolutional kernels. The complexity of the flame edge can be quantified by calculating the fractal dimension. Specifically, the flame edge can be binarized, and the fractal dimension can be estimated using box-counting. The higher the value, the more intense the combustion and the more complex the structure. Finally, based on the convolutional neural network, the shallow features (edges, colors) and deep semantic features (shapes, motion trends) can be fused through skip connections to extract the static features such as flame color and edge fractal dimension corresponding to the target analysis image.

[0035] Optionally, the average brightness value of the target analysis image can be extracted from consecutive image frames to form a time series. A fast Fourier transform can be performed on the brightness series to identify the main frequency components and obtain the flicker frequency. If the flicker frequency of the flame is concentrated in the range of 5~15Hz, it can be used as a key criterion to exclude interference from static light sources. Optical flow analysis can also be performed in conjunction with adjacent image frames to confirm that the flame area has random jumping characteristics rather than a fixed bright object, so as to obtain visual features.

[0036] S103. Based on the preset fusion strategy, determine the fire confidence level of a fire occurring in the target cabin according to temperature characteristics, gas characteristics and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

[0037] Among them, the pre-defined fusion strategy refers to a strategy that combines a long short-term memory network model and a pre-defined evidence theory to analyze temperature characteristics, gas characteristics, and visual characteristics to determine the fire confidence level. The fire determination result refers to the result of assessing whether a fire warning should be issued.

[0038] Optionally, based on a preset fusion strategy, the fire confidence level of a fire occurring in the target compartment is determined according to temperature features, gas features, and visual features. This includes: extracting features from temperature features, gas features, and visual features respectively based on a multi-branch long short-term memory network to obtain multimodal joint features; using a preset fully connected layer to determine the initial fire confidence level corresponding to the multimodal joint features; and based on the initial fire confidence level, performing multi-source fusion decision-making based on a preset evidence theory to determine the fire confidence level of a fire occurring in the target compartment.

[0039] The multi-branch Long Short-Term Memory (LSTM) network can include a temperature gradient LSTM branch, a gas concentration LSTM branch, and a visual feature LSTM branch. The temperature gradient LSTM branch takes temperature features as input, i.e., a temperature gradient time series (e.g., generating a data point every 5 seconds), and outputs a hidden layer state vector representing the persistence and acceleration of the temperature rise trend, capturing "slow smoldering" or "rapid deflagration" patterns. The gas concentration LSTM branch takes gas features as input and outputs an embedding vector of multi-gas change patterns, identifying typical fire precursors (e.g., a pyrolysis sequence where H2 rises first, followed by CO). The visual feature LSTM branch takes visual features as input and outputs a dynamic visual behavior representation, distinguishing real flames from interference sources (e.g., vehicle lights, reflections). Each LSTM branch outputs a low-dimensional feature vector, collectively forming a multimodal joint feature.

[0040] The presupposed evidence theory can be the DS evidence theory (Dempster-Schaffer evidence theory). The initial fire confidence level can include three independent local fire confidence levels, corresponding to the judgment criteria of temperature, gas, and vision, respectively: temperature-based local fire confidence level, gas-based local fire confidence level, and vision-based local fire confidence level.

[0041] Optionally, the outputs of each LSTM branch can be connected to an independent fully connected layer to output local fire confidence scores based on temperature, gas, and vision, respectively.

[0042] Optionally, based on the DS evidence theory, an identification framework Θ={fire, non-fire} can be constructed, and the three sensor sources (temperature, gas, and vision) can be regarded as independent evidence sources. The weighting factor of each independent evidence source can be determined by adaptively adjusting the strategy based on sensor credibility or environmental stability. The weighting factor of each independent evidence source and the confidence of local fire based on temperature, local fire based on gas, and local fire based on vision are weighted and summed to obtain the final fire confidence of fire occurring in the target compartment.

[0043] Optionally, if the fire confidence level of the final target compartment is greater than the preset fire threshold (e.g., 0.7), the fire determination result can be determined as having a high probability of fire occurrence, and a fire warning operation can be performed to respond to the fire determination request.

[0044] Optionally, a fuzzy logic rule base and a transfer learning mechanism can be constructed. The fusion model is based on a land fire dataset and uses adaptive weight adjustment: dynamically adjusting sensor weights according to the environment (such as cabin ventilation) (e.g., reducing the weight of gas sensors and strengthening the vision module); and anti-interference technology: (dual-band infrared filtering to suppress welding interference, microwave resonance technology to eliminate dust) to reduce misjudgments and increase accuracy, that is, to perform multi-source fusion decision-making to determine the fire confidence level of a fire occurring in the target cabin.

[0045] The technical solution of this invention, in response to a fire determination request within a target compartment, determines sensor data collected by preset temperature sensors, gas sensors, and visual sensors; analyzes and processes the temperature data, gas concentration data, and visual image data from the sensor data to obtain temperature features, gas features, and visual features; based on a preset fusion strategy, determines the fire confidence level of a fire occurring within the target compartment according to the temperature features, gas features, and visual features, thereby determining the fire determination result and responding to the fire determination request. By conducting a more comprehensive analysis of the fire situation from three levels—temperature, gas concentration, and visual recognition—and combining this with a preset fusion strategy to quickly assess the fire confidence level, the timeliness and accuracy of fire identification can be effectively improved.

[0046] Example 2 Figure 2 This is a structural block diagram of a fire determination device provided in an embodiment of the present invention. This embodiment is applicable to situations where a more comprehensive analysis of a fire situation is performed from three levels: temperature, gas concentration, and visual recognition. Combined with a preset fusion strategy, it quickly assesses the fire confidence level. The fire determination device provided by the present invention can execute the fire determination method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the execution method. This fire determination device can be implemented in hardware and / or software and configured in an electronic device with fire determination function, such as... Figure 2 As shown, the fire detection device may specifically include: The determination module 201 is used to determine the sensor data collected by the preset temperature sensor, gas sensor and vision sensor in response to the fire determination request in the target compartment. Analysis module 202 is used to analyze and process the temperature data, gas concentration data and visual image data in the sensing data respectively to obtain temperature features, gas features and visual features; The response module 203 is used to determine the fire confidence level of a fire occurring in the target compartment based on a preset fusion strategy, according to temperature characteristics, gas characteristics and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

[0047] The technical solution of this invention, in response to a fire determination request within a target compartment, determines sensor data collected by preset temperature sensors, gas sensors, and visual sensors; analyzes and processes the temperature data, gas concentration data, and visual image data from the sensor data to obtain temperature features, gas features, and visual features; based on a preset fusion strategy, determines the fire confidence level of a fire occurring within the target compartment according to the temperature features, gas features, and visual features, thereby determining the fire determination result and responding to the fire determination request. By conducting a more comprehensive analysis of the fire situation from three levels—temperature, gas concentration, and visual recognition—and combining this with a preset fusion strategy to quickly assess the fire confidence level, the timeliness and accuracy of fire identification can be effectively improved.

[0048] Furthermore, the target compartment refers to the vehicle compartment inside the ship; temperature sensors are respectively configured at at least two temperature measuring points on the top of the vehicle compartment; gas sensors are configured at the bottom of the vehicle compartment; and vision sensors are configured on the top of the vehicle compartment. Module 201 is specifically used for: The local temperature inside the target cabin is collected by a pre-set distributed fiber optic temperature detector, and the spatial temperature distribution map inside the target cabin is collected by an infrared thermal imager in order to determine the temperature data collected by the pre-set temperature sensor. A preset gas detector is used to detect the gas concentration of the target gas inside the target chamber in order to determine the gas concentration data collected by the gas sensor. A pre-set visible light dual-mode camera is used to collect video data inside the target cabin for a preset duration in order to determine the visual image data collected by the visual sensor.

[0049] Furthermore, the analysis module 202 is specifically used for: Determine the temperature data in the sensing data; the temperature data includes the local temperature collected by the distributed fiber optic temperature detector and the temperature distribution map collected by the infrared thermal imager; The local temperature collected by the distributed fiber optic temperature detectors during the preset analysis period is analyzed to determine the local temperature rise rate. Based on the temperature distribution map collected by the infrared thermal imager and the preset high temperature threshold, the area ratio of high temperature region in the temperature distribution map is determined, and the temperature characteristics are determined based on the local temperature rise rate and the area ratio of high temperature region.

[0050] Furthermore, the analysis module 202 is also used for: Determine the gas concentration data of the target gas in the sensing data; the target gas includes at least one of the following: carbon monoxide, hydrogen, and hydrocarbon gas; Baseline calibration of gas concentration data is performed based on a preset dynamic threshold method to eliminate background noise and obtain calibrated gas concentration data. Based on the calibrated gas concentration data, an initial eigenvector is determined, and the initial eigenvector is normalized and subjected to principal component analysis to obtain the principal component score matrix, which serves as the gas feature.

[0051] Furthermore, the analysis module 202 is also used for: A preset target detection model is used to perform target detection on the visual image data in the sensor data to obtain the target analysis image corresponding to the flame area. Feature extraction is performed on the target analysis image based on a pre-trained convolutional neural network to determine the flame color, edge fractal dimension, and flashing frequency corresponding to the target analysis image, thereby obtaining visual features.

[0052] Furthermore, the response module 203 is specifically used for: Based on a multi-branch long short-term memory network, feature extraction is performed on temperature features, gas features and visual features respectively to obtain multimodal joint features; A pre-defined fully connected layer is used to determine the initial fire confidence level corresponding to the multimodal joint features. Based on the initial fire confidence level, a multi-source fusion decision is made according to the pre-defined evidence theory to determine the fire confidence level of a fire occurring in the target compartment.

[0053] Example 3 Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Figure 3 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0054] like Figure 3As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0055] Multiple components in electronic device 10 are connected to input / output 15, including: input unit 16, such as a keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as a disk, optical disk, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0056] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as fire determination methods.

[0057] In some embodiments, the fire determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the fire determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the fire determination method by any other suitable means (e.g., by means of firmware).

[0058] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), system-on-a-chip (SoCs), complex programmable logic devices (PLCs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0059] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0060] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0061] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (e.g., voice input, speech input, or tactile input).

[0062] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0063] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual reality services, such as high management difficulty and weak business scalability.

[0064] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the fire determination method of any embodiment of the present invention.

[0065] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0066] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0067] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a fire, characterized in that, include: In response to a request to determine a fire in the target compartment, the sensor data collected by the preset temperature sensor, gas sensor and vision sensor are determined. Temperature data, gas concentration data, and visual image data from the sensor data are analyzed and processed to obtain temperature characteristics, gas characteristics, and visual characteristics. Based on a pre-defined fusion strategy, the fire confidence level of a fire occurring in the target compartment is determined according to temperature characteristics, gas characteristics, and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

2. The method according to claim 1, characterized in that, in, The target compartment refers to the vehicle compartment inside the ship; temperature sensors are respectively configured at at least two temperature measuring points on the top of the vehicle compartment; gas sensors are configured at the bottom of the vehicle compartment; and vision sensors are configured on the top of the vehicle compartment. Accordingly, the sensor data acquired by the preset temperature sensor, gas sensor, and vision sensor are determined, including: The local temperature inside the target cabin is collected by a pre-set distributed fiber optic temperature detector, and the spatial temperature distribution map inside the target cabin is collected by an infrared thermal imager in order to determine the temperature data collected by the pre-set temperature sensor. A preset gas detector is used to detect the gas concentration of the target gas inside the target chamber in order to determine the gas concentration data collected by the gas sensor. A pre-set visible light dual-mode camera is used to collect video data inside the target cabin for a preset duration in order to determine the visual image data collected by the visual sensor.

3. The method according to claim 1, characterized in that, The temperature data in the sensor data is analyzed and processed to obtain temperature characteristics, including: Determine the temperature data in the sensing data; the temperature data includes the local temperature collected by the distributed fiber optic temperature detector and the temperature distribution map collected by the infrared thermal imager; The local temperature collected by the distributed fiber optic temperature detectors during the preset analysis period is analyzed to determine the local temperature rise rate. Based on the temperature distribution map collected by the infrared thermal imager and the preset high temperature threshold, the area ratio of high temperature region in the temperature distribution map is determined, and the temperature characteristics are determined based on the local temperature rise rate and the area ratio of high temperature region.

4. The method according to claim 1, characterized in that, The gas concentration data in the sensor data is analyzed and processed to obtain gas characteristics, including: Determine the gas concentration data of the target gas in the sensing data; the target gas includes at least one of the following: carbon monoxide, hydrogen, and hydrocarbon gas; Baseline calibration of gas concentration data is performed based on a preset dynamic threshold method to eliminate background noise and obtain calibrated gas concentration data. Based on the calibrated gas concentration data, an initial eigenvector is determined, and the initial eigenvector is normalized and subjected to principal component analysis to obtain the principal component score matrix, which serves as the gas feature.

5. The method according to claim 1, characterized in that, Visual image data from sensor data is analyzed and processed to obtain visual features, including: A preset target detection model is used to perform target detection on the visual image data in the sensor data to obtain the target analysis image corresponding to the flame area. Feature extraction is performed on the target analysis image based on a pre-trained convolutional neural network to determine the flame color, edge fractal dimension, and flashing frequency corresponding to the target analysis image, thereby obtaining visual features.

6. The method according to claim 1, characterized in that, Based on a pre-defined fusion strategy, the fire confidence level for a fire occurring inside the target compartment is determined according to temperature characteristics, gas characteristics, and visual characteristics, including: Based on a multi-branch long short-term memory network, feature extraction is performed on temperature features, gas features and visual features respectively to obtain multimodal joint features; A pre-defined fully connected layer is used to determine the initial fire confidence level corresponding to the multimodal joint features. Based on the initial fire confidence level, a multi-source fusion decision is made according to the pre-defined evidence theory to determine the fire confidence level of a fire occurring in the target compartment.

7. A fire detection device, characterized in that, include: The determination module is used to determine the sensor data collected by the preset temperature sensor, gas sensor and vision sensor in response to the fire determination request in the target compartment. The analysis module is used to analyze and process the temperature data, gas concentration data and visual image data in the sensor data respectively to obtain temperature features, gas features and visual features. The response module is used to determine the fire confidence level of a fire occurring in the target compartment based on a preset fusion strategy, according to temperature characteristics, gas characteristics, and visual characteristics, so as to determine the fire determination result and respond to the fire determination request.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor, such that the at least one processor is able to perform the fire determination method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the fire determination method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fire determination method according to any one of claims 1-6.

Images