Method for determining fireproof performance of firewall, storage medium and electronic equipment

Abstract

The invention relates to the field of firewall testing, in particular to a firewall fireproof performance determination method, a storage medium and electronic equipment. Comprising the following steps: splicing each feature vector corresponding to a temperature time sequence image, strain time sequence data, a firewall type identifier and a burning time length into an environment feature vector; and inputting the environment feature vector into the target LSTM model, and generating a stability result of the negative pressure environment in the future time period corresponding to the current time. And adjusting the air pressure of the negative pressure chamber at a corresponding moment by using negative pressure equipment according to a stability result. When the firewall test is carried out, the rule of each time sequence characteristic in the historical time period is captured through the trained target LSTM model to accurately predict the sealing change of the negative pressure cavity in the future time period, so that the adjustment can be carried out in time at the corresponding moment in the future time period according to various negative pressure adjusting devices, and the sealing performance of the negative pressure cavity is improved. The stability of the air pressure in the negative pressure chamber in the whole experiment process is maintained, so that the experiment can be smoothly completed.

Description

Background Art

[0002] The aircraft engine nacelle structure is one of the key components of the aircraft, mainly including the air inlet, fan cover, reverse thrust internal and external devices, and tail nozzle structure. Its function is to wrap the engine and its system accessories. During flight, it mainly bears aerodynamic loads and plays a rectifying role. At the same time, it also takes into account anti-icing, fire prevention, noise prevention, installation and maintenance functions. A fire in an aircraft power unit will pose a serious threat to flight safety. If the flames escape from the engine nacelle, they may spread to the wing fuel tank or fuselage, causing a major accident with the destruction of the aircraft and the death of people. Therefore, it is very necessary to study the fire protection design of the engine nacelle structure. Among them, the firewall design of structures such as the engine nacelle of civil aircraft is the focus of model aircraft design and an important review item for model airworthiness certification.

[0003] In the design of civil aircraft fire protection systems, it should be ensured that any fire in the fire zone will not cause harm to the aircraft. Firewalls are an important safety measure to achieve this goal. Their main function is to limit the fire to the engine nacelle or auxiliary power unit compartment when a fire occurs in the fire zone, and prevent the flame from penetrating into the adjacent fuselage or wing parts to reduce the danger caused by the fire. In addition, firewalls can also prevent exhaust gas and hot air from passing through the firewall and entering the crew and passenger cabins.

[0004] In order to ensure that the fireproof performance of the firewall can reach the corresponding standard level, the corresponding experimental device will be set up in advance to test and determine the fireproof performance of the firewall. Among them, in addition to the firewall body, the firewall also includes the through-wall joints of the firewall, and the through-wall joints of the firewall should be sealed with fireproof seals. Fireproof seals are usually distributed in different areas such as the hanging cavity, fan cavity, core cavity, fan duct, etc. Usually, due to the pressure difference between the fire zone and the non-fire zone, the corresponding pressure environment is also provided for the test piece of the firewall during the fireproof test, that is, a negative pressure is formed on the back of the test firewall to simulate the actual use environment.

[0005] In the prior art, as the fire prevention experiment proceeds, the cavity structure that provides the negative pressure environment will deform as the temperature rises, which will cause deformation at the joints, ultimately resulting in damage to the airtightness of the cavity, which will cause a sudden change in the air pressure in the cavity, destroying the experimental conditions and making the experiment impossible to complete. Summary of the invention

[0006] In view of the above technical problems, the technical solution adopted by the present invention is:

[0007] According to one aspect of the present invention, a method for determining the fireproof performance of a fire wall is provided, which is applied to a fireproof verification system. The fireproof verification system includes a burner assembly and a negative pressure assembly on the back of a test piece. The burner assembly is used to provide a flame of a preset temperature for the test fire wall, and the negative pressure assembly on the back of the test piece is used to fix the test fire wall and provide a preset negative pressure environment in the test fire wall.

[0008] The method comprises the following steps:

[0009] The test parameters are determined according to the type of fire wall under test, including: flame parameters, fire prevention / fire resistance level, back negative pressure and test time.

[0010] The fire wall to be tested is clamped on the negative pressure assembly at the back of the test piece, and the negative pressure assembly at the back of the test piece is controlled to generate a corresponding negative pressure environment according to the negative pressure at the back.

[0011] According to the flame parameters, fire protection / fire resistance level and test time, the burner assembly is adjusted to spray the corresponding flame to the preset area on the front of the test firewall.

[0012] According to the initial state image of the tested firewall and the ablation state diagrams corresponding to different time nodes, the performance level corresponding to the tested firewall is generated.

[0013] The back negative pressure component maintains the stability of the negative pressure environment according to the following steps:

[0014] Obtain the temperature time series image, strain time series data, firewall type identification and burning time of the test piece clamping plate in the historical period corresponding to the current time.

[0015] Each frame of the temperature image in the temperature time series image is input into the target convolutional neural network, and the preset intermediate output of the target convolutional neural network is obtained as the feature vector corresponding to each frame of the temperature image.

[0016] Each feature vector corresponding to the temperature time series image, strain time series data, firewall type identification and burning duration are spliced ​​into an environmental feature vector.

[0017] The environmental feature vector is input into the target LSTM model to generate the stability results of the negative pressure environment in the future period corresponding to the current time. The stability results include the chamber seal is intact, the environmental negative pressure is stable, and the chamber seal is damaged, and the environmental negative pressure decreases.

[0018] According to the stability results, the negative pressure device is used to adjust the air pressure of the negative pressure chamber at the corresponding time.

[0019] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for determining the fire protection performance of a firewall is implemented.

[0020] According to a third aspect of the present invention, there is provided 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 the above-mentioned method for determining the fire protection performance of a firewall when executing the computer program.

[0021] The present invention has at least the following beneficial effects:

[0022] In the present invention, the sealing destruction of the negative pressure cavity is a process that continues over time and is related to the time series. Therefore, in the present invention, when conducting a firewall test, the temperature, strain, burning time and other time series data in the negative pressure cavity are used to indicate the changing characteristics of the negative pressure cavity, and the trained target LSTM model is used to capture the rules of each time series feature in the historical period to accurately predict the sealing changes of the negative pressure cavity in the future period. Therefore, various negative pressure regulating devices can be adjusted in time at the corresponding moments in the future period to maintain the stability of the air pressure in the negative pressure chamber during the entire experiment to ensure that the experiment can be completed smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A flowchart of a method for determining the fire protection performance of a firewall provided in an embodiment of the present invention.

[0025] Figure 2 A schematic structural diagram of a burner and a flame calibration device provided in an embodiment of the present invention.

[0026] Figure 3 A schematic diagram of the structure of the negative pressure assembly on the back of the test piece provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] As a possible embodiment of the present invention, Figure 1As shown, a method for determining the fireproof performance of a fire wall is provided, which is applied to a fireproof verification system. The fireproof verification system includes a burner assembly and a negative pressure assembly on the back of a test piece. The burner assembly is used to provide a flame of a preset temperature for the test fire wall, and the negative pressure assembly on the back of the test piece is used to fix the test fire wall and provide a preset negative pressure environment in the test fire wall.

[0029] Specifically, the burner assembly can be a Carlin oil burner 1, such as Figure 2 As shown, the Carlin oil burner 1 is a gun-type burner, the nozzle is required to maintain a certain oil pressure, and at the same time, a standard flame can be generated by adjusting the burner oil pressure and air volume.

[0030] like Figure 3 As shown, the negative pressure assembly on the back of the test piece includes: a test piece clamping plate 2, a chamber shell 3, a vacuum pump 4, a pressure gauge 7 and an observation window 5.

[0031] The test piece clamping plate 2 is fixedly connected to the chamber shell 3 to form a negative pressure chamber. A negative pressure port is provided on the test piece clamping plate 2 to provide back negative pressure for the test fire wall. The test fire wall is fixedly connected to the test piece clamping plate 2, and its back is placed in the area corresponding to the negative pressure port.

[0032] The vacuum pump 4 and the observation window 5 are both fixedly connected to the chamber shell 3. The chamber shell 3 is provided with an air inlet 6, and the air inlet 6 and the vacuum pump 4 are both used to adjust the air pressure in the negative pressure chamber. The observation window 5 is used to observe from the back whether the test firewall is burned through. The pressure gauge 7 is connected to the negative pressure chamber. The pressure gauge 7 is used to monitor the air pressure in the negative pressure chamber in real time.

[0033] The method for determining the fire protection performance of a firewall comprises the following steps:

[0034] S100: Determine the test parameters according to the type of the fire wall under test, the test parameters include: flame parameters, fire prevention / fire resistance level, back negative pressure and test time.

[0035] S200: The test firewall is clamped on the negative pressure assembly at the back of the test piece, and the negative pressure assembly at the back of the test piece is controlled to generate a corresponding negative pressure environment according to the negative pressure at the back.

[0036] S300: According to the flame parameters, fire protection / fire resistance level and test time, adjust the burner assembly to spray the corresponding flame to the preset area on the front of the test firewall.

[0037] S400: Generate a performance level corresponding to the firewall under test according to the initial state image of the firewall under test and the ablation state diagrams corresponding to different time nodes.

[0038] The above steps S100 to S400 are an overview of the steps for conducting a fire performance test, and the specific steps can be carried out as follows:

[0039] a) Check the appearance of the test piece, take photos and record the situation (cracks and defects are not allowed).

[0040] b) Calibration position debugging: Place the thermocouple rake (consisting of 7 thermocouples) at a distance of (100±10) mm from the outlet end face of the burner cone, with the end of the thermocouple located at (25±1) mm above the center line of the burner. The heat flow meter is located at the end of the fourth thermocouple of the thermocouple rake.

[0041] c) Flame parameter debugging: Place the thermocouple comb on the test bench, place the burner in the preheating position, ignite the burner, preheat for 5 minutes, move the thermocouple to the test position after preheating, collect temperature data of 7 thermocouples (collection time is 30 seconds, and calculate the average value, sampling frequency is 1 second), and confirm that the temperature reaches 1100℃±80℃; move the thermocouple comb to the preheating position, and then move the heat flow meter to the test position to confirm that the heat flow value is 10.6W / cm 2 ~12.6W / cm 2 range; if the heat flux or temperature value is not within the required range, the burner should be debugged until the flame temperature and heat flux value meet the requirements.

[0042] d) According to the working conditions, start the vibration test bench system, the airflow control system on the back of the test piece, and the negative pressure control system on the back of the test piece as needed and set the parameters, and set the operating time of each system as needed.

[0043] e) Select the shooting angle and prepare for the shooting.

[0044] f) The flame covers an area of ​​at least 10 in × 10 in (254 mm × 254 mm) of the test piece, meeting the requirements of AC 20-135.

[0045] g) Install the test piece on the specimen holder according to the test piece installation method described above.

[0046] h) Turn on the burner, preheat for 5 minutes, quickly position the burner to the test position and start timing, and perform a 5-minute fire resistance / 15-minute fire protection test on the test piece according to the test conditions. If the fire wall is observed to burn through, record the burn-through time and stop the flame impact. Record the test phenomenon.

[0047] i) If the test piece burns through or breaks during the test, the time of the burn-through or breakage should be recorded.

[0048] j) After the test time is reached, measure the flame temperature and heat flux of the burner again.

[0049] k) Turn off the burner and take a photo of the test piece after combustion.

[0050] The back negative pressure component maintains the stability of the negative pressure environment according to the following steps:

[0051] S201: Obtaining the temperature time series image, strain time series data, firewall type identification and burning duration of the test piece clamping plate 2 in the historical period corresponding to the current time.

[0052] Specifically, the historical period corresponding to the current time includes the period within 3S before the current time. The future period corresponding to the current time includes the period within 2S after the current time. The length of the historical period in this embodiment can also be determined based on how long it takes for the negative pressure chamber internal environment to change accordingly before the negative pressure chamber seal has problems. In addition, the future period should not be set too long, because the confidence level corresponding to the later time in the results predicted by the LSTM (Long Short-Term Memory, a special recurrent neural network) model will drop rapidly.

[0053] The temperature time series image includes the infrared image of the test piece clamping plate 2 acquired at each acquisition moment in the historical period. The strain time series data includes: the strain data of multiple acquisition points on the test piece clamping plate 2 and the test firewall acquired at each acquisition moment in the historical period. The data acquisition frequency can be determined according to the actual usage, such as once per second. In this way, the temperature time series image, strain time series data, firewall type identification and burning time corresponding to each current moment can be collected. The firewall type identification in this embodiment can be determined according to the specific type of the test firewall. Usually, the types of the test firewalls include rubber seal firewalls (P type and Ω type), sealant firewalls (overlap configuration) and maze firewalls.

[0054] After S201 processing, the initial data corresponding to each moment can be obtained, and after subsequent processing, it can be input into the target LSTM model for prediction calculation. Among them, the temperature image data can be converted into corresponding vector data according to the following S202 scheme.

[0055] S202: Each frame of the temperature image in the temperature time series image is input into the target convolutional neural network, and a preset intermediate output of the target convolutional neural network is obtained as a feature vector corresponding to each frame of the temperature image. The temperature image in this embodiment may be an infrared temperature image.

[0056] Since the input form of the LSTM model is usually a three-dimensional tensor, it is necessary to convert the temperature image into input data in the form of a vector. In this embodiment, the intermediate layer output of the pre-trained model of the convolutional neural network (CNN) is used as the feature vector of the image. This method can often extract higher-level abstract features. The target convolutional neural networks in this embodiment are all models that have completed pre-training in large-scale image data sets (such as ImageNet), such as VGG, ResNet, etc. This can use the previously learned knowledge to accelerate and optimize the feature extraction process of infrared images, making the model more efficient and accurate when processing this type of specific type of image.

[0057] Generally, the vector output by the later intermediate layer can better represent the semantic information in the image, and the vector output by the earlier intermediate layer can better represent the texture information in the image. In this embodiment, the outputs of the two earlier and later intermediate layers can be selected for splicing as the feature vector corresponding to the temperature image. Of course, a certain layer of the pre-trained model (usually the second to last layer, that is, the layer before the fully connected layer) can be directly used as a feature extractor, the infrared temperature image can be input into the model, and the extracted feature vector can be used for subsequent prediction processing. The dimension of the feature vector can be determined according to the specific CNN model.

[0058] In addition, if the dimension of the feature vector is very high, you can use methods such as PCA (Principal Component Analysis), t-SNE (t-distributed Stochastic Neighbor Embedding), or LDA (Linear Discriminant Analysis) to reduce the dimension to reduce computational complexity and remove redundant information.

[0059] Before each frame of the temperature image in the temperature time series image is input into the target convolutional neural network, the method further includes:

[0060] S212: grayscale each frame of the temperature image to generate a temperature grayscale image corresponding to each frame of the temperature image.

[0061] Since the temperature image collected by the infrared camera is a three-channel RGB image, it is necessary to convert the image into a single-channel one. First, it is converted into a grayscale image because most feature extraction models process single-channel images.

[0062] S222: Normalize the temperature grayscale image to generate a normalized data image corresponding to each frame of the temperature image. The normalized value A corresponding to the mth pixel in the i-th frame of the temperature image is i m The following conditions must be met:

[0063] Ai m =B i m / 255. Among them, B i m A i m The corresponding grayscale value.

[0064] In this step, the temperature data in the infrared temperature image is normalized to a specific range (0-1) for subsequent processing.

[0065] S232: Perform Gaussian filtering on each normalized data graph to generate a standard feature graph corresponding to each frame of temperature image.

[0066] In this step, the application of Gaussian filtering can reduce the noise in the image. After the pre-processing from S212 to S232, the image data input into the target convolutional neural network can be made more standardized, thereby improving the accuracy of the conversion into vector data.

[0067] S203: Each feature vector corresponding to the temperature time series image, the strain time series data, the firewall type identifier and the burning duration are spliced ​​into an environmental feature vector.

[0068] In the fire performance test of the test firewall, strain gauges are also placed on the firewall. Strain gauges are mainly used to measure the strain (i.e., shape change) of materials or structures under stress. They can be used to monitor the mechanical response of the test firewall structure under simulated fire tests or extreme conditions, and evaluate whether its structural strength and stability meet safety requirements. The strain time series data in this embodiment can be the strain data of the test firewall. It is also possible to place corresponding strain gauges at corresponding detection positions on the test piece clamping plate 2 in advance, and then collect the strain data of the test firewall and the test piece clamping plate 2 together.

[0069] In this embodiment, the environmental characteristic vector is obtained through S203, and the temperature data and the strain data can roughly reflect the general situation of the thermal deformation of the negative pressure cavity, and further reflect the situation of the damage of the negative pressure cavity seal.

[0070] S204: Input the environmental feature vector into the target LSTM model to generate the stability result of the negative pressure environment in the future period corresponding to the current time. The stability result includes the chamber seal is intact, the environmental negative pressure is stable, and the chamber seal is damaged, and the environmental negative pressure decreases.

[0071] The target LSTM is a trained LSTM model, and the corresponding training samples are obtained through the test data of historical fire prevention experiments. The form of the sample data is the same as the form of the input target LSTM in the present invention. The corresponding sample label is the change value of the air pressure in each second in the future period relative to the experimental set air pressure, which can be obtained from the historical records of the barometer. Taking the future period of 2 seconds as an example, if the air pressure remains unchanged within 2 seconds, the label is 0,0, and the sample corresponding to the label is a positive sample. If the air pressure increases at a rate of 10Pa per second within 2 seconds, the label is 10,20, and the sample is a negative sample.

[0072] S205: According to the stability result, the negative pressure device is used to adjust the air pressure of the negative pressure chamber at the corresponding time.

[0073] In this step, the vacuum pump 4 and the opening degree of the air inlet 6 can be adjusted to adjust the negative pressure chamber at a future time to ensure that the air pressure in the negative pressure chamber does not change significantly due to seal damage and heat. At the same time, the air pressure is also adjusted by the pressure value fed back by the pressure gauge 7 to avoid incorrect adjustment of the air pressure due to inaccurate model prediction results. Therefore, the stability of the air pressure in the negative pressure chamber can be further improved by adjusting the two dimensions together.

[0074] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0075] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0076] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0077] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0078] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0079] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0080] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0081] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0082] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0083] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0084] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may communicate with one or more devices that enable a user to interact with the electronic device, and / or may communicate with any device (e.g., routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0085] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0086] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0087] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0088] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0089] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0090] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0091] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0092] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0093] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for determining the fire protection performance of a firewall, characterized in that: Applied to a fire prevention verification system, the fire prevention verification system comprises a burner assembly and a negative pressure assembly at the back of a test piece, the burner assembly is used to provide a flame of a preset temperature for the test fire wall, and the negative pressure assembly at the back of the test piece is used to fix the test fire wall and provide a preset negative pressure environment at the test fire wall; The method comprises the following steps: Determine the experimental parameters according to the type of the tested firewall, the experimental parameters including: flame parameters, fire prevention / fire resistance level, back negative pressure and experimental time; The test firewall is clamped on the negative pressure assembly at the back of the test piece, and the negative pressure assembly at the back of the test piece is controlled to generate a corresponding negative pressure environment according to the negative pressure at the back; According to the flame parameters, fire prevention / fire resistance level and test time, adjusting the burner assembly to spray corresponding flames toward the preset area on the front of the test fire wall; Generate a performance level corresponding to the tested firewall according to the initial state image of the tested firewall and the ablation state diagrams corresponding to different time nodes; The back negative pressure assembly maintains the stability of the negative pressure environment according to the following steps: Obtain the temperature time series image, strain time series data, firewall type identification and burning time of the test piece clamping plate in the historical period corresponding to the current time; Input each frame of the temperature image in the temperature time series image into the target convolutional neural network, and obtain a preset intermediate output of the target convolutional neural network as a feature vector corresponding to each frame of the temperature image; Each feature vector, strain time series data, firewall type identifier and burning duration corresponding to the temperature time series image are spliced ​​into an environmental feature vector; Input the environmental feature vector into the target LSTM model to generate a stability result of the negative pressure environment in the future period corresponding to the current time; the stability result includes that the chamber seal is intact, the environmental negative pressure is stable, and the chamber seal is damaged, and the environmental negative pressure decreases; According to the stability result, the air pressure of the negative pressure chamber is adjusted at the corresponding time using a negative pressure device.

2. The method according to claim 1, characterized in that Before inputting each frame of the temperature image in the temperature time series image into the target convolutional neural network, the method further includes: Grayscale each frame of temperature image to generate a temperature grayscale image corresponding to each frame of temperature image; The temperature grayscale image is normalized to generate a normalized data image corresponding to each frame of the temperature image; wherein the normalized value A corresponding to the mth pixel in the i-th frame of the temperature image is i m The following conditions must be met: A i m =B i m / 255; among them, B i m A i m The corresponding grayscale value.

3. The method according to claim 2, characterized in that After generating a normalized data graph corresponding to each frame of the temperature image, the method further includes: Gaussian filtering is performed on each normalized data graph to generate a standard feature graph corresponding to each frame of temperature image.

4. The method according to claim 1, characterized in that: The historical period corresponding to the current time includes the period within 3S before the current time.

5. The method according to claim 1, characterized in that The future time period corresponding to the current time includes a time period within 2S after the current time.

6. The method according to claim 1, characterized in that The temperature time series image includes an infrared image of the test piece clamping plate acquired at each acquisition moment in a historical period.

7. The method according to claim 1, characterized in that The strain time series data includes strain data of multiple acquisition points on the test piece clamping plate and the test fire wall acquired at each acquisition moment in the historical period.

8. The method according to claim 1, characterized in that The negative pressure assembly on the back of the test piece includes: a test piece clamping plate, a chamber shell, a vacuum pump, a pressure gauge and an observation window; The test piece clamping plate is fixedly connected to the chamber shell to form a negative pressure chamber; a negative pressure port is provided on the test piece clamping plate to provide back negative pressure for the test firewall; The vacuum pump and the observation window are both fixedly connected to the chamber shell; an air suction port is provided on the chamber shell, and the air suction port and the vacuum pump are both used to adjust the air pressure in the negative pressure chamber; The pressure gauge is communicated with the negative pressure chamber.

9. A non-transitory computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for determining the fire protection performance of a firewall as claimed in any one of claims 1 to 8 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for determining the fire protection performance of a firewall as described in any one of claims 1 to 8 is implemented.

Images