Fire alarm detection system, fire alarm detection method and rail vehicle

Abstract

The invention provides a fire alarm detection system, a fire alarm detection method and a rail vehicle, the fire alarm detection system is applied to the rail vehicle, and the system comprises a plurality of fire detection devices of different types, the fire detection devices of different types are arranged in to-be-detected areas, matched with detection characteristics of the fire detection devices, in the railway vehicle and used for generating fire detection results of the to-be-detected areas, and the fire alarm controller is in communication connection with the fire detection devices and used for sending the fire detection results to the to-be-detected areas. And the alarm module is used for receiving the fire detection result sent by each fire detection device and generating an alarm signal based on the fire detection result. According to the invention, different fire detection devices are adopted in different to-be-detected areas for fire detection, and the fire alarm accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of internal combustion motor vehicle multiple units, and in particular to a fire alarm detection system, a fire alarm detection method and a rail vehicle. Background Art

[0002] In existing diesel locomotives, the smoke and fire alarm system is an important safety equipment, and its design and configuration are directly related to the safety and reliability of train operation.

[0003] However, most current fire and smoke alarm systems in internal combustion engine vehicles often only use a single type of detector, such as a fire detector, to monitor fire and smoke signals. In internal combustion engine vehicles in semi-enclosed areas, fire alarms based on a single detector are prone to false alarms.

[0004] Therefore, finding a fire alarm detection system that can improve the accuracy of fire alarms has become a current research hotspot. Summary of the Invention

[0005] The present invention provides a fire alarm detection system, a fire alarm detection method and a rail vehicle, which realize fire detection by using different fire detection devices in different areas to be detected, thereby improving the accuracy of fire alarm.

[0006] The present invention provides a fire alarm detection system, which is applied to a rail vehicle. The system includes: a plurality of different types of fire detection devices, wherein the different types of fire detection devices are arranged in areas to be detected in the rail vehicle that match the detection characteristics of each of the fire detection devices, and are used to generate fire detection results in the areas to be detected; and a fire alarm controller, which is communicatively connected to each of the fire detection devices, is used to receive the fire detection results sent by each of the fire detection devices, and generate an alarm signal based on the fire detection results.

[0007] According to a fire alarm detection system provided by the present invention, the fire alarm detection system includes at least two fire alarm controllers arranged in different areas of the rail vehicle, wherein the at least two fire alarm controllers receive fire detection results sent by each fire detection device in parallel, and generate an alarm signal based on the fire detection results, so as to ensure the normal operation of the fire alarm detection system in the event of a failure of any one of the fire alarm controllers.

[0008] According to a fire alarm detection system provided by the present invention, different types of fire detection devices include at least a temperature-sensing cable module, a fire detector, and a flame detector; different types of fire detection devices are arranged in areas to be detected in the rail vehicle that match the detection characteristics of each fire detection device, and are implemented in the following manner: the temperature-sensing cable module is arranged in an internal area of ​​a working equipment in the rail vehicle that matches the detection characteristics of the temperature-sensing cable module, wherein the working equipment represents an equipment component used to maintain the normal operation of the rail vehicle; the fire detector is arranged in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; and the flame detector is arranged in an internal area of ​​an internal combustion engine room in the rail vehicle that matches the detection characteristics of the flame detector.

[0009] According to a fire alarm detection system provided by the present invention, the fire alarm detection system also includes: an image acquisition module, which is communicatively connected to the fire alarm controller and is used to acquire a regional image of the area to be detected in the rail vehicle, so that the fire alarm controller generates a comprehensive fire detection result based on the regional image and the fire detection result, and generates an alarm signal based on the comprehensive fire detection result.

[0010] According to a fire alarm detection system provided by the present invention, the fire alarm controller adopts the following method to generate a comprehensive fire detection result based on the area image and the fire detection result: based on the area image, determining the infrared thermal imaging image corresponding to the area image; calling a pre-trained fire detection model, and inputting the infrared thermal imaging image and the fire detection result into the fire detection model to obtain the comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

[0011] According to a fire alarm detection system provided by the present invention, the fire alarm controller trains the fire detection model in the following manner: obtaining a comprehensive fire detection result output by the fire detection model, as well as the infrared thermal imaging image and the fire detection result input into the fire detection model corresponding to the comprehensive fire detection result; using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to iteratively train the fire detection model again to obtain an iteratively trained fire detection model; and using the iteratively trained fire detection model as the fire detection model.

[0012] According to a fire alarm detection system provided by the present invention, the fire detection device generates the fire detection result of the area to be detected in the following manner: collecting the fire detection signal of the area to be detected; and processing the fire detection signal based on edge computing to generate the fire detection result of the area to be detected.

[0013] The present invention also provides a fire alarm detection method, which is applied to rail vehicles. The method includes: obtaining fire detection results of the area to be detected in the rail vehicle generated by different types of fire detection devices, wherein the different types of fire detection devices are arranged in the area to be detected in the rail vehicle that matches the detection characteristics of each fire detection device; and generating an alarm signal based on the fire detection results.

[0014] According to a fire alarm detection method provided by the present invention, different types of fire detection devices include at least a temperature-sensing cable module, a fire detector, and a flame detector; different types of fire detection devices are arranged in areas to be detected in the rail vehicle that match the detection characteristics of each fire detection device, specifically including: the temperature-sensing cable module is arranged in an internal area of ​​a working equipment in the rail vehicle that matches the detection characteristics of the temperature-sensing cable module, wherein the working equipment represents an equipment component used to maintain the normal operation of the rail vehicle; the fire detector is arranged in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; the flame detector is arranged in an internal area of ​​an internal combustion engine room in the rail vehicle that matches the detection characteristics of the flame detector.

[0015] According to a fire alarm detection method provided by the present invention, before generating an alarm signal based on the fire detection result, the method further includes: acquiring a regional image of the area to be detected in the rail vehicle; generating an alarm signal based on the fire detection result specifically includes: generating a comprehensive fire detection result based on the regional image and the fire detection result, and generating an alarm signal based on the comprehensive fire detection result.

[0016] According to a fire alarm detection method provided by the present invention, a comprehensive fire detection result is generated based on the area image and the fire detection result, and an alarm signal is generated based on the comprehensive fire detection result, specifically including: determining an infrared thermal imaging image corresponding to the area image based on the area image; calling a pre-trained fire detection model, and inputting the infrared thermal imaging image and the fire detection result into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

[0017] According to a fire alarm detection method provided by the present invention, the fire detection model is trained in the following manner: obtaining a comprehensive fire detection result output by the fire detection model, and the infrared thermal imaging image and the fire detection result input into the fire detection model corresponding to the comprehensive fire detection result; using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to iteratively train the fire detection model again to obtain an iteratively trained fire detection model; and using the iteratively trained fire detection model as the fire detection model.

[0018] The present invention also provides a fire alarm detection virtual device, which is applied to a rail vehicle. The virtual device includes: an acquisition module for acquiring fire detection results of an area to be detected in the rail vehicle generated by different types of fire detection devices, wherein the different types of fire detection devices are arranged in an area to be detected in the rail vehicle that matches the detection characteristics of each fire detection device; and a generation module for generating an alarm signal based on the fire detection results.

[0019] The present invention also provides a rail vehicle, comprising: a rail vehicle body, which is a diesel motor vehicle body, and a fire alarm detection system built into the rail vehicle, wherein the fire alarm detection system is any one of the fire alarm detection systems described.

[0020] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described fire alarm detection methods when executing the computer program.

[0021] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the fire alarm detection methods described above.

[0022] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the fire alarm detection methods described above.

[0023] The present invention provides a fire alarm detection system, a fire alarm detection method, and a rail vehicle. The fire alarm detection system is applied to a rail vehicle and comprises: a plurality of different types of fire detection devices; and a fire alarm controller. The different types of fire detection devices are arranged in areas to be detected on the rail vehicle that match the detection characteristics of each fire detection device, and are used to generate fire detection results in the areas to be detected. The fire alarm controller is communicatively connected to each fire detection device, is used to receive the fire detection results sent by each fire detection device, and generates an alarm signal based on the fire detection results. This enables the use of different fire detection devices for fire detection in different areas to be detected, thereby improving the accuracy of fire alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0025] Figure 1 It is a structural diagram of the fire alarm detection system provided by the present invention.

[0026] Figure 2 It is a flow chart of different types of fire detection devices provided by the present invention being arranged in a rail vehicle and the areas to be detected matching the detection characteristics of each fire detection device.

[0027] Figure 3 It is a schematic diagram of a process for generating a comprehensive fire detection result based on a regional image and a fire detection result provided by the present invention.

[0028] Figure 4 It is a schematic diagram of the process of training the fire detection model provided by the present invention.

[0029] Figure 5 It is a flow chart of the fire alarm detection method provided by the present invention.

[0030] Figure 6 It is a structural diagram of the fire alarm detection virtual device provided by the present invention.

[0031] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention.

[0032] Description of reference numerals: 100: Fire alarm detection system; 101: Fire detection device; 102: Fire alarm controller. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0034] The fire alarm detection system provided by this invention utilizes different monitoring devices (corresponding to different fire detection devices) in different environments (corresponding to different detection areas). It monitors smoke concentration, ambient temperature, and other information in real time and transmits this information to a fire alarm controller via a communications network. The fire alarm controller then outputs the fire alarm status to the audible and visual alarm buttons on the driver's cab console, prompting prompt action to address the situation. This invention improves the redundancy of the fire alarm detection system and ensures the reliability of the smoke and fire alarm system.

[0035] Figure 1 It is a structural diagram of the fire alarm detection system provided by the present invention.

[0036] The following will be combined Figure 1 The structure of the fire alarm detection system provided by the present invention is described.

[0037] In an exemplary embodiment of the present invention, the fire alarm detection system can be applied to a rail vehicle. Figure 1 It can be seen that the fire alarm detection system 100 may include a plurality of fire detection devices 101 of different types, and a fire alarm controller 102. Each component will be described below.

[0038] In one example, different types of fire detection devices 101 can be installed in rail vehicles in areas to be detected that match the detection characteristics of each fire detection device 101, generating fire detection results for the areas to be detected. For example, for areas to be detected in large, sealed environments, the optical detection characteristics of the fire detector can be used to perform corresponding detection on these areas. For smaller areas to be detected, such as the interior of working equipment, the flexible detection characteristics of the temperature-sensing cable module can be used to perform corresponding detection on the interior of the working equipment.

[0039] In this embodiment, according to the characteristics of different areas to be detected, corresponding types of fire detection devices 101 are configured and called to perform corresponding detections to obtain fire detection results, which can improve the accuracy of the fire detection results.

[0040] In another embodiment, the fire alarm controller 102 is in communication with each fire detection device 101 , and is configured to receive fire detection results sent by each fire detection device 101 , and generate an alarm signal based on the fire detection results.

[0041] During application, the fire alarm controller 102 can form a system through a communication network, with each fire detection device 101 being a network node; the fire alarm controller 102 manages each fire detection device 101 in real time through its internal bus, and can monitor the working status of each device, fire alarm information and internal network bus status in real time, and display them on the smoke and fire alarm system display screen.

[0042] The present invention provides a fire alarm detection system for use on rail vehicles. The system comprises: multiple fire detection devices of different types, each of which is installed in a target area of ​​the rail vehicle that matches the detection characteristics of each fire detection device, and a fire alarm controller. The fire alarm controller is communicatively connected to each fire detection device, receives the fire detection results sent by each fire detection device, and generates an alarm signal based on the fire detection results. This system utilizes different fire detection devices for fire detection in different target areas, improving the accuracy of fire alarms.

[0043] In another exemplary embodiment of the present invention, the fire alarm detection system 100 includes at least two fire alarm controllers 102 disposed in different areas of a rail vehicle, wherein: At least two fire alarm controllers 102 receive the fire detection results sent by each fire detection device 101 in parallel, and generate an alarm signal based on the fire detection results, so that the fire alarm detection system 100 can operate normally when any fire alarm controller 102 fails.

[0044] In one embodiment, two fire alarm controllers 102 are used as an example. In practice, one fire alarm controller 102 can be installed at each of the front and rear cars of a rail vehicle. Because both fire alarm controllers 102 receive fire detection results from the fire detection devices 101 in parallel, the entire fire alarm detection system 100 can continue to operate normally even if one fire alarm controller 102 fails. In this embodiment, the redundant configuration of the fire alarm controllers 102 effectively improves the redundancy of the fire alarm detection system 100 and ensures its reliability.

[0045] Figure 2It is a flow chart of different types of fire detection devices provided by the present invention being arranged in a rail vehicle and the areas to be detected matching the detection characteristics of each fire detection device.

[0046] The following will be combined Figure 2 The process of arranging different types of fire detection devices in a rail vehicle in areas to be detected that match the detection characteristics of each fire detection device is described.

[0047] In an exemplary embodiment of the present invention, different types of fire detection devices may include at least a temperature sensing cable module, a fire detector, and a flame detector. Figure 2 It can be seen that the following steps may be included for arranging different types of fire detection devices in a rail vehicle in an area to be detected that matches the detection characteristics of each fire detection device: In step 210 , the temperature sensing cable module is disposed in an internal area of ​​a working device in a rail vehicle that matches a detection characteristic of the temperature sensing cable module, wherein the working device represents a device component for maintaining normal operation of the rail vehicle.

[0048] In one embodiment, a temperature-sensing cable module can detect the ambient air temperature using a temperature-sensing resistor. When the temperature around the detector reaches a certain value, the detector will report a fire alarm to the controller. The alarm temperature threshold is adjustable. The temperature-sensing cable module offers a certain degree of flexibility, allowing for detection within confined areas of working equipment. In another embodiment, the working equipment may include components such as batteries, traction converters, and auxiliary converters in rail vehicles.

[0049] In step 220 , a fire detector is installed in a confined space area of ​​the rail vehicle that matches the detection characteristics of the fire detector.

[0050] In another embodiment, the fire detector is an optical sensor, which includes a light source, an emitting lens and a photodetector installed at an appropriate angle. If there are no smoke particles in the detection chamber, the light source will directly illuminate the wall of the detection chamber, and the photodetector will not receive the light. If there are smoke particles in the detection chamber, the light source will be refracted by these particles, and the refracted light will be received by the photodetector. The intensity of the refracted light represents the concentration of the smoke. The fire detector has a pollution compensation function, and the sensitivity can be adjusted according to different environmental data to ensure that the sensitivity of all detectors is consistent. During application, corresponding detection can be performed on the area to be detected with a large and sealed environmental feature. Among them, the enclosed space area can include the interior of the car, such as the passenger compartment and the driver's cab.

[0051] In step 230 , a flame detector is disposed in a region within an internal combustion engine compartment of a rail vehicle that matches the detection characteristics of the flame detector.

[0052] The flame detector first receives signals from three narrow-band pyroelectric infrared sensors with significantly different response characteristics to flames, sunlight, and artificial heat sources. After filtering and amplifying them respectively through a low-pass filter, the analog signals are converted into digital signals through an analog-to-digital converter (A / D). Then, a high-performance microcontroller and dedicated algorithms are used to perform dual processing and judgment in the time domain and frequency domain. This can quickly and accurately detect fire conditions and has strong resistance to thermal interference. This avoids the weakness of traditional infrared flame detectors that are easily interfered with by background heat sources and light, thereby improving the working stability and application range of infrared flame detectors.

[0053] During application, corresponding detection can be performed based on flame detectors for areas inside the internal combustion engine room where flames may be generated.

[0054] In the aforementioned embodiments, corresponding fire detection devices may be used to perform fire detection in areas to be detected under different environments, thereby improving the accuracy of fire detection results.

[0055] In another exemplary embodiment of the present invention, the fire alarm detection system 100 may further include an image acquisition module. The image acquisition module is communicatively coupled to the fire alarm controller 102 and configured to capture an image of the area to be detected in the rail vehicle, enabling the fire alarm controller 102 to generate a comprehensive fire detection result based on the image and the fire detection result, and to generate an alarm signal based on the comprehensive fire detection result.

[0056] In one embodiment, to further improve the accuracy of the generated alarm signal, in addition to the fire detection results generated by the fire detection device 101, a regional image of the area to be detected is also referenced. Furthermore, a comprehensive fire detection result can be generated based on both the regional image and the fire detection results, and an alarm signal can be generated based on the comprehensive fire detection result. This embodiment combines multiple pieces of information to determine the final comprehensive fire detection result, effectively improving the accuracy and reliability of the alarm signal.

[0057] Figure 3 It is a schematic diagram of a process for generating a comprehensive fire detection result based on a regional image and a fire detection result provided by the present invention.

[0058] The following will be combined Figure 3 The process of generating comprehensive fire detection results based on regional images and fire detection results is described.

[0059] In an exemplary embodiment of the present invention, Figure 3It can be seen that generating a comprehensive fire detection result based on the regional image and the fire detection result may include step 310 and step 320, and each step will be described below.

[0060] In step 310 , based on the regional image, an infrared thermal imaging image corresponding to the regional image is determined.

[0061] In step 320, a pre-trained fire detection model is called, and the infrared thermal imaging image and the fire detection result are input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model.

[0062] In one embodiment, an infrared thermal image corresponding to the regional image can be determined based on the regional image. Since the infrared thermal image can indicate whether a fire has occurred to a certain extent, during application, a final comprehensive fire detection result can be determined based on the infrared thermal image and the fire detection result.

[0063] In another embodiment, a pre-trained fire detection model can be invoked and the infrared thermal image and fire detection results can be input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model. The fire detection model is used to determine the comprehensive fire detection result based on the infrared thermal image and the fire detection results. This embodiment effectively improves the accuracy and reliability of alarm signals by combining the infrared thermal image and the fire detection results to determine the final comprehensive fire detection result.

[0064] Figure 4 It is a schematic diagram of the process of training the fire detection model provided by the present invention.

[0065] The following will be combined Figure 4 The process of training a fire detection model is described.

[0066] In an exemplary embodiment of the present invention, Figure 4 It can be seen that training the fire detection model may include steps 410 to 430, and each step will be described below.

[0067] In step 410 , the comprehensive fire detection result output by the fire detection model, as well as the infrared thermal imaging image input to the fire detection model and the fire detection result corresponding to the comprehensive fire detection result are obtained.

[0068] In step 420, the fire detection model is iteratively trained again using the comprehensive fire detection results, infrared thermal imaging images, and fire detection results as training data to obtain an iteratively trained fire detection model.

[0069] In one embodiment, continuing with the above Figure 3Take the following example to illustrate: Figure 3 The fire detection model outputs a comprehensive fire detection result obtained in the manner described above, and then obtains an infrared thermal image and fire detection result corresponding to the comprehensive fire detection result, which are then input into the fire detection model. Furthermore, the aforementioned set of correspondence information can be used as training data for the fire detection model, and the fire detection model can be iteratively trained again to obtain an iteratively trained fire detection model. It is understood that the iteratively trained fire detection model, due to the rich training data, can further improve the accuracy of the comprehensive fire detection results it outputs.

[0070] In step 430 , the iteratively trained fire detection model is used as the fire detection model.

[0071] In one embodiment, the iteratively trained fire detection model may be used as the fire detection model, thereby effectively ensuring the accuracy of the subsequent comprehensive fire detection results output based on the fire detection model.

[0072] In another exemplary embodiment of the present invention, the fire detection device may generate a fire detection result of the area to be detected in the following manner: Collect fire detection signals in the area to be detected; Based on edge computing, the fire detection signal is processed to generate the fire detection results of the area to be detected.

[0073] In one embodiment, preliminary processing of fire detection signals can be performed in a fire detection device, and corresponding fire detection results can be extracted. Through edge computing of the fire detection device, the response speed of the fire alarm detection system can be effectively improved.

[0074] In another embodiment, after generating an alarm signal, the fire alarm detection system sends the signal to a host computer of the rail vehicle. The host computer monitors the video linkage in the rail vehicle and retrieves the image of the location of the alarm.

[0075] As described above, the present invention provides a fire alarm detection system for use on rail vehicles. The system comprises: multiple fire detection devices of different types; and a fire alarm controller. The different types of fire detection devices are positioned in areas of the rail vehicle to be detected that match the detection characteristics of each fire detection device, and are configured to generate fire detection results in those areas. The fire alarm controller is communicatively connected to each fire detection device, receiving the fire detection results transmitted by each fire detection device and generating an alarm signal based on the fire detection results. This system utilizes different fire detection devices for fire detection in different areas to be detected, thereby improving the accuracy of fire alarms.

[0076] Based on the same inventive concept, the present application also provides a fire alarm detection method.

[0077] Figure 5 It is a flow chart of the fire alarm detection method provided by the present invention.

[0078] The following will be combined Figure 5 The process of the fire alarm detection method provided by the present invention is described.

[0079] In another exemplary embodiment of the present invention, the fire alarm detection method can be applied to a rail vehicle. Figure 5 It can be seen that the fire alarm detection method may include step 510 and step 520, and each step will be introduced below.

[0080] In step 510, fire detection results of the to-be-detected area in the rail vehicle generated by different types of fire detection devices are obtained, wherein the different types of fire detection devices are arranged in the to-be-detected area in the rail vehicle that matches the detection characteristics of each fire detection device.

[0081] In step 520, an alarm signal is generated based on the fire detection result.

[0082] In one embodiment, different types of fire detection devices can be installed in rail vehicles in areas to be detected that match the detection characteristics of each fire detection device, generating fire detection results in the areas to be detected. Furthermore, an alarm signal is generated based on the fire detection results. In this embodiment, corresponding types of fire detection devices are configured and invoked based on the characteristics of different areas to be detected, performing corresponding detections to obtain fire detection results. Alarm signals are then generated based on the fire detection results, thereby improving the accuracy of fire alarms.

[0083] In yet another exemplary embodiment of the present invention, different types of fire detection devices may include at least a temperature sensing cable module, a fire detector, and a flame detector; Different types of fire detection devices are arranged in the rail vehicle in areas to be detected that match the detection characteristics of each fire detection device. This can be achieved in the following ways: The temperature sensing cable module is arranged in an internal area of ​​a working device in a rail vehicle that matches a detection characteristic of the temperature sensing cable module, wherein the working device represents a device component used to maintain normal operation of the rail vehicle; The fire detector is installed in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; The flame detector is arranged in an area inside the internal combustion engine compartment of the rail vehicle that matches the detection characteristics of the flame detector.

[0084] In one embodiment, the temperature sensing cable module has a certain degree of flexibility, so it can be used to detect the internal area of ​​a narrow working device. In another embodiment, the working device may include equipment components such as batteries, traction converters, and auxiliary converters in a rail vehicle.

[0085] In another embodiment, the corresponding detection can be performed on a to-be-detected area that has a large and sealed environment. The enclosed space area can include the interior of a vehicle compartment, such as a passenger compartment and a driver's cab.

[0086] In yet another embodiment, corresponding detection can be performed based on a flame detector for the area inside the engine compartment where flames may be generated.

[0087] In the aforementioned embodiments, corresponding fire detection devices may be used to perform fire detection in areas to be detected under different environments, thereby improving the accuracy of fire detection results.

[0088] In another exemplary embodiment of the present invention, continuing with the above Figure 5 Taking the above embodiment as an example, before generating an alarm signal based on the fire detection result (corresponding to step 520), the fire alarm detection method may further include the following steps: Collecting regional images of the area to be inspected in the rail vehicle; The following methods can be used to generate an alarm signal based on the fire detection results: A comprehensive fire detection result is generated based on the regional image and the fire detection result, and an alarm signal is generated based on the comprehensive fire detection result.

[0089] In one embodiment, to further improve the accuracy of the generated alarm signal, in addition to the fire detection results generated by the fire detection device, a regional image of the area to be detected is also referenced. Furthermore, a comprehensive fire detection result can be generated based on both the regional image and the fire detection results, and an alarm signal can be generated based on the comprehensive fire detection result. This embodiment, by combining multiple pieces of information to determine the final comprehensive fire detection result, can effectively improve the accuracy and reliability of the alarm signal.

[0090] In another exemplary embodiment of the present invention, generating a comprehensive fire detection result based on the regional image and the fire detection result, and generating an alarm signal based on the comprehensive fire detection result can be implemented in the following manner: Based on the regional image, determining an infrared thermal imaging image corresponding to the regional image; A pre-trained fire detection model is called, and the infrared thermal imaging image and the fire detection result are input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

[0091] In one embodiment, an infrared thermal image corresponding to the regional image can be determined based on the regional image. Since the infrared thermal image can indicate whether a fire has occurred to a certain extent, during application, a final comprehensive fire detection result can be determined based on the infrared thermal image and the fire detection result.

[0092] Furthermore, a pre-trained fire detection model can be invoked and the infrared thermal image and fire detection results can be input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model. The fire detection model is used to determine the comprehensive fire detection result based on the infrared thermal image and the fire detection results. This embodiment combines the infrared thermal image and the fire detection results to determine the final comprehensive fire detection result, effectively improving the accuracy and reliability of the alarm signal.

[0093] In another exemplary embodiment of the present invention, the fire detection model is trained in the following manner: Obtaining a comprehensive fire detection result output by the fire detection model, and the infrared thermal imaging image input into the fire detection model and the fire detection result corresponding to the comprehensive fire detection result; Iteratively training the fire detection model again using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to obtain an iteratively trained fire detection model; The fire detection model after iterative training is used as the fire detection model.

[0094] In one embodiment, continuing with the aforementioned embodiment as an example, a comprehensive fire detection result output by a fire detection model can be obtained, and then an infrared thermal image corresponding to the comprehensive fire detection result and input to the fire detection model, as well as the fire detection result, can be obtained. Furthermore, the aforementioned set of correspondence information can be used as training data for the fire detection model, and the fire detection model can be iteratively trained again to obtain an iteratively trained fire detection model. It is understood that the resulting iteratively trained fire detection model, due to the richness of the training data, can further improve the accuracy of the comprehensive fire detection results it outputs.

[0095] Furthermore, the fire detection model after iterative training can be used as a fire detection model, thereby effectively ensuring the accuracy of the subsequent comprehensive fire detection results output based on the fire detection model.

[0096] The fire alarm detection virtual device provided by the present invention is described below. The fire alarm detection virtual device described below and the fire alarm detection method described above can be referenced to each other.

[0097] Figure 6 It is a structural diagram of the fire alarm detection virtual device provided by the present invention.

[0098] The following will be combined Figure 6 The structure of the fire alarm detection virtual device provided by the present invention is described.

[0099] In an exemplary embodiment of the present invention, the fire alarm detection virtual device can be applied to rail vehicles, combined with Figure 6 It can be seen that the virtual device may include an acquisition module 610 and a generation module 620, and each module will be introduced below.

[0100] The acquisition module 610 may be configured to acquire fire detection results of the to-be-detected area in the rail vehicle generated by different types of fire detection devices, wherein the different types of fire detection devices are arranged in the to-be-detected area in the rail vehicle that matches the detection characteristics of each fire detection device; The generating module 620 may be configured to generate an alarm signal based on the fire detection result.

[0101] In an exemplary embodiment of the present invention, different types of fire detection devices include at least a temperature sensing cable module, a fire detector, and a flame detector; The acquisition module 610 may implement the following methods to arrange different types of fire detection devices in the rail vehicle in the area to be detected that matches the detection characteristics of each fire detection device: The temperature-sensing cable module is disposed in an internal area of ​​a working device in the rail vehicle that matches a detection characteristic of the temperature-sensing cable module, wherein the working device represents a device component used to maintain normal operation of the rail vehicle; The fire detector is arranged in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; The flame detector is arranged in an area inside the internal combustion engine compartment of the rail vehicle that matches the detection characteristics of the flame detector.

[0102] In an exemplary embodiment of the present invention, the generating module 620 may also be configured to: Acquiring a regional image of the area to be detected in the rail vehicle; The generation module 620 may generate an alarm signal based on the fire detection result in the following manner: A comprehensive fire detection result is generated based on the area image and the fire detection result, and an alarm signal is generated based on the comprehensive fire detection result.

[0103] In an exemplary embodiment of the present invention, the generation module 620 may generate a comprehensive fire detection result based on the regional image and the fire detection result, and generate an alarm signal based on the comprehensive fire detection result in the following manner: Based on the regional image, determining an infrared thermal imaging image corresponding to the regional image; A pre-trained fire detection model is called, and the infrared thermal imaging image and the fire detection result are input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

[0104] In an exemplary embodiment of the present invention, the generation module 620 may implement the training to obtain the fire detection model in the following manner: Obtaining a comprehensive fire detection result output by the fire detection model, and the infrared thermal imaging image input into the fire detection model and the fire detection result corresponding to the comprehensive fire detection result; Iteratively training the fire detection model again using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to obtain an iteratively trained fire detection model; The fire detection model after iterative training is used as the fire detection model.

[0105] Based on the same inventive concept, the present invention further provides a rail vehicle, which will be described below in conjunction with the following embodiments.

[0106] In an exemplary embodiment of the present invention, a rail vehicle may include: A rail vehicle body, the rail vehicle body being a diesel vehicle train body, and A fire alarm detection system built into the rail vehicle, wherein the fire alarm detection system is the fire alarm detection system described in any one of the above embodiments.

[0107] Through this embodiment, different fire detection devices are used to perform fire detection in different areas to be detected, thereby improving the accuracy of fire alarms on rail vehicles.

[0108] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740. The processor 710, the communications interface 720, and the memory 730 communicate with each other via the communications bus 740. The processor 710 may invoke logic instructions in the memory 730 to execute a fire alarm detection method, which is applied to a rail vehicle. The method includes: obtaining fire detection results generated by different types of fire detection devices for a to-be-detected area in the rail vehicle, wherein the different types of fire detection devices are disposed in the to-be-detected area in the rail vehicle that match the detection characteristics of each fire detection device; and generating an alarm signal based on the fire detection results.

[0109] Furthermore, the logic instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the fire alarm detection method provided by the above-mentioned methods. The fire alarm detection method is applied to a rail vehicle, and the method includes: obtaining fire detection results of the area to be detected in the rail vehicle generated by different types of fire detection devices, wherein different types of fire detection devices are arranged in the area to be detected in the rail vehicle that matches the detection characteristics of each of the fire detection devices; and generating an alarm signal based on the fire detection results.

[0111] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the fire alarm detection method provided by the above-mentioned methods. The fire alarm detection method is applied to a rail vehicle, and the method includes: obtaining fire detection results of an area to be detected in the rail vehicle generated by different types of fire detection devices, wherein different types of fire detection devices are arranged in areas to be detected in the rail vehicle that match the detection characteristics of each of the fire detection devices; and generating an alarm signal based on the fire detection results.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0113] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A fire alarm detection system, characterized in that: The fire alarm detection system is applied to a rail vehicle, and the system comprises: A plurality of different types of fire detection devices, wherein the different types of fire detection devices are arranged in the rail vehicle in areas to be detected that match the detection characteristics of each of the fire detection devices, and are used to generate fire detection results in the areas to be detected, as well as A fire alarm controller is communicatively connected to each of the fire detection devices, and is used to receive fire detection results sent by each of the fire detection devices and generate an alarm signal based on the fire detection results.

2. The fire alarm detection system according to claim 1, characterized in that: The fire alarm detection system comprises at least two fire alarm controllers arranged in different areas of the rail vehicle, wherein: At least two of the fire alarm controllers receive the fire detection results sent by the fire detection devices in parallel, and generate alarm signals based on the fire detection results, so that the fire alarm detection system can operate normally when any one of the fire alarm controllers fails.

3. The fire alarm detection system according to claim 1, characterized in that: Different types of fire detection devices include at least temperature sensing cable modules, fire detectors, and flame detectors; Different types of fire detection devices are arranged in the rail vehicle in areas to be detected that match the detection characteristics of each fire detection device, and this is achieved in the following manner: The temperature-sensing cable module is disposed in an internal area of ​​a working device in the rail vehicle that matches a detection characteristic of the temperature-sensing cable module, wherein the working device represents a device component used to maintain normal operation of the rail vehicle; The fire detector is arranged in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; The flame detector is arranged in an area inside the internal combustion engine compartment of the rail vehicle that matches the detection characteristics of the flame detector.

4. The fire alarm detection system according to claim 1, characterized in that: The fire alarm detection system further comprises: An image acquisition module is communicatively connected to the fire alarm controller and is used to acquire a regional image of the area to be detected in the rail vehicle, so that the fire alarm controller generates a comprehensive fire detection result based on the regional image and the fire detection result, and generates an alarm signal based on the comprehensive fire detection result.

5. The fire alarm detection system according to claim 4, characterized in that: The fire alarm controller generates a comprehensive fire detection result based on the regional image and the fire detection result in the following manner: Based on the regional image, determining an infrared thermal imaging image corresponding to the regional image; A pre-trained fire detection model is called, and the infrared thermal imaging image and the fire detection result are input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

6. The fire alarm detection system according to claim 5, characterized in that: The fire alarm controller trains the fire detection model in the following manner: Obtaining a comprehensive fire detection result output by the fire detection model, and the infrared thermal imaging image input into the fire detection model and the fire detection result corresponding to the comprehensive fire detection result; Iteratively training the fire detection model again using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to obtain an iteratively trained fire detection model; The fire detection model after iterative training is used as the fire detection model.

7. The fire alarm detection system according to any one of claims 1 to 6, characterized in that: The fire detection device generates the fire detection result of the area to be detected in the following manner: Collecting fire detection signals from the area to be detected; Based on edge computing, the fire detection signal is processed to generate a fire detection result for the area to be detected.

8. A fire alarm detection method, characterized in that: The fire alarm detection method is applied to a rail vehicle, and the method comprises: Obtaining fire detection results of a to-be-detected area in the rail vehicle generated by different types of fire detection devices, wherein the different types of fire detection devices are arranged in the to-be-detected area in the rail vehicle that matches the detection characteristics of each fire detection device; Based on the fire detection result, an alarm signal is generated.

9. The fire alarm detection method according to claim 8, characterized in that: Different types of fire detection devices include at least temperature sensing cable modules, fire detectors, and flame detectors; Different types of fire detection devices are arranged in the rail vehicle in areas to be detected that match the detection characteristics of each fire detection device, specifically including: The temperature-sensing cable module is disposed in an internal area of ​​a working device in the rail vehicle that matches a detection characteristic of the temperature-sensing cable module, wherein the working device represents a device component used to maintain normal operation of the rail vehicle; The fire detector is arranged in a confined space area in the rail vehicle that matches the detection characteristics of the fire detector; The flame detector is arranged in an area inside the internal combustion engine compartment of the rail vehicle that matches the detection characteristics of the flame detector.

10. The fire alarm detection method according to claim 8 or 9, characterized in that: Before generating an alarm signal based on the fire detection result, the method further includes: Acquiring a regional image of the area to be detected in the rail vehicle; The generating of an alarm signal based on the fire detection result specifically includes: A comprehensive fire detection result is generated based on the area image and the fire detection result, and an alarm signal is generated based on the comprehensive fire detection result.

11. The fire alarm detection method according to claim 10, characterized in that: Generating a comprehensive fire detection result based on the regional image and the fire detection result, and generating an alarm signal based on the comprehensive fire detection result, specifically includes: Based on the regional image, determining an infrared thermal imaging image corresponding to the regional image; A pre-trained fire detection model is called, and the infrared thermal imaging image and the fire detection result are input into the fire detection model to obtain a comprehensive fire detection result output by the fire detection model, wherein the fire detection model is used to jointly determine the comprehensive fire detection result based on the infrared thermal imaging image and the fire detection result.

12. The fire alarm detection method according to claim 11, characterized in that: The fire detection model is trained in the following way: Obtaining a comprehensive fire detection result output by the fire detection model, and the infrared thermal imaging image input into the fire detection model and the fire detection result corresponding to the comprehensive fire detection result; Iteratively training the fire detection model again using the comprehensive fire detection result, the infrared thermal imaging image, and the fire detection result as training data to obtain an iteratively trained fire detection model; The fire detection model after iterative training is used as the fire detection model.

13. A fire alarm detection virtual device, characterized in that: The fire alarm detection virtual device is applied to a rail vehicle, and the virtual device includes: an acquisition module, configured to acquire fire detection results of a to-be-detected area in the rail vehicle generated by different types of fire detection devices, wherein the different types of fire detection devices are arranged in the to-be-detected area in the rail vehicle that matches the detection characteristics of each fire detection device; A generating module is used to generate an alarm signal based on the fire detection result.

14. A rail vehicle, wherein: The rail vehicle comprises: A rail vehicle body, the rail vehicle body being a diesel vehicle train body, and A fire alarm detection system built into the rail vehicle, wherein the fire alarm detection system is the fire alarm detection system according to any one of claims 1 to 7.

Images